Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    technical terms and medical terminologies related to health conditions and treatments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is essentially inert—it never activates on any tokens in these examples and thus doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dossier
    -0.06
    PP
    -0.06
     pcm
    -0.06
    .digital
    -0.06
    анием
    -0.06
     声
    -0.06
    iyorlar
    -0.06
    ylinder
    -0.06
     birlik
    -0.06
     Gates
    -0.06
    POSITIVE LOGITS
     населення
    0.06
    arez
    0.06
    _ASC
    0.06
     хв
    0.06
    _predict
    0.06
    があり
    0.06
    Compression
    0.06
    libc
    0.06
     discovered
    0.06
    。
    0.06
    Act Density 0.004%

    No Known Activations