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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Calls
    -0.06
    \ActiveForm
    -0.06
     color
    -0.06
    izzes
    -0.06
     gd
    -0.06
    研
    -0.05
    elog
    -0.05
     nt
    -0.05
     NF
    -0.05
     रख
    -0.05
    POSITIVE LOGITS
     pillow
    0.08
    dictionary
    0.07
     special
    0.07
    chunk
    0.07
    scatter
    0.06
    _item
    0.06
     jamais
    0.06
    ({});↵
    0.06
    จาก
    0.06
    .allow
    0.06
    Act Density 0.003%

    No Known Activations