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

    Neuronpedia

    INDEX
    Explanations

    Chat logs/forum posts

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it never reliably fires and doesn’t respond to any token pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    485
    -0.06
    hopefully
    -0.06
    �
    -0.06
     스
    -0.06
    but
    -0.06
    �
    -0.06
    θν
    -0.06
     (('
    -0.06
    webpack
    -0.06
    ظة
    -0.06
    POSITIVE LOGITS
     IIC
    0.07
    .Local
    0.06
     вч
    0.06
     NUMBER
    0.06
     helm
    0.06
    etri
    0.06
     Sheila
    0.06
    _NOW
    0.06
    /API
    0.06
     funnel
    0.06
    Act Density 0.067%

    No Known Activations