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

    Neuronpedia

    INDEX
    Explanations

    Describing physical objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (QIcon
    -0.08
    ोश
    -0.07
    example
    -0.07
    (cv
    -0.07
     freeing
    -0.07
    -efficient
    -0.07
    铁
    -0.07
    -0.07
     Мед
    -0.06
    olit
    -0.06
    POSITIVE LOGITS
     Lawrence
    0.07
     NOR
    0.06
     Pussy
    0.06
     serialized
    0.06
     Maggie
    0.06
    _motor
    0.06
     sàng
    0.06
     refriger
    0.05
     yasal
    0.05
    　↵
    0.05
    Act Density 0.095%

    No Known Activations