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

    Neuronpedia

    INDEX
    Explanations

    code parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="../../
    -0.06
     mask
    -0.06
    рос
    -0.06
    angepicker
    -0.06
     tasted
    -0.06
    thy
    -0.06
     活
    -0.06
    ёт
    -0.06
     MESSAGE
    -0.06
    Provides
    -0.06
    POSITIVE LOGITS
    elerinden
    0.07
     Walls
    0.07
    组织
    0.07
     {-
    0.07
     BYTE
    0.07
     thủ
    0.06
    abile
    0.06
     URLSession
    0.06
     prote
    0.06
    .create
    0.06
    Act Density 0.001%

    No Known Activations