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

    Neuronpedia

    INDEX
    Explanations

    Income statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @brief
    -0.07
    .Unmarshal
    -0.07
    \Service
    -0.06
     Patch
    -0.06
    -comm
    -0.06
    -version
    -0.06
    _format
    -0.06
    _regularizer
    -0.06
     Filtering
    -0.06
    .clients
    -0.06
    POSITIVE LOGITS
    amon
    0.07
    MEDIA
    0.07
     حالی
    0.07
    dsa
    0.06
    star
    0.06
    -rest
    0.06
    cono
    0.06
     mesh
    0.06
     Definitely
    0.06
    233
    0.06
    Act Density 0.000%

    No Known Activations