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

    Neuronpedia

    INDEX
    Explanations

    Enthusiasts or lovers of things

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive and does not detect any specific tokens or patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Storage
    -0.07
     MIDI
    -0.07
     strife
    -0.07
     Fraud
    -0.06
    ानद
    -0.06
    writes
    -0.06
    UPPORTED
    -0.06
    atted
    -0.06
    apture
    -0.06
     zkou
    -0.06
    POSITIVE LOGITS
    district
    0.07
    .numero
    0.07
    .desc
    0.07
     AB
    0.07
    ":"
    0.06
     degradation
    0.06
    น
    0.06
    ّا
    0.06
     침
    0.06
    .search
    0.06
    Act Density 0.023%

    No Known Activations