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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bye
    -0.07
    Find
    -0.06
    ToObject
    -0.06
    Finder
    -0.06
     Create
    -0.06
     surprise
    -0.06
    OfClass
    -0.06
     drop
    -0.06
    اسب
    -0.06
    oundation
    -0.06
    POSITIVE LOGITS
    zones
    0.07
     Tomas
    0.07
     ￥
    0.07
    .axis
    0.06
    〔
    0.06
     vypad
    0.06
    �
    0.06
    řej
    0.06
    \xd
    0.06
    _des
    0.06
    Act Density 0.002%

    No Known Activations