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

    Neuronpedia

    INDEX
    Explanations

    -transparent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :
↵
    -0.07
    _profile
    -0.07
    .collider
    -0.07
    -b
    -0.07
    แฟ
    -0.06
    OMEM
    -0.06
    .ByteArray
    -0.06
     fais
    -0.06
     �
    -0.06
     ПО
    -0.06
    POSITIVE LOGITS
    .trace
    0.08
     enlightenment
    0.07
    depending
    0.07
     Enlightenment
    0.06
    foods
    0.06
     Cone
    0.06
    fern
    0.06
     boyfriend
    0.06
     etkili
    0.06
    债
    0.06
    Act Density 0.000%

    No Known Activations