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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孩子
    -0.07
     INTO
    -0.07
     Desk
    -0.07
     Sik
    -0.06
    _fold
    -0.06
    ARY
    -0.06
    "c
    -0.06
    past
    -0.06
    Police
    -0.06
     Sai
    -0.06
    POSITIVE LOGITS
     соглас
    0.06
     δημο
    0.06
     amacıyla
    0.06
     наличии
    0.06
    ;element
    0.06
     Liberia
    0.06
     doctrines
    0.06
     القر
    0.06
    -important
    0.06
     прем
    0.06
    Act Density 0.001%

    No Known Activations