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

    Neuronpedia

    INDEX
    Explanations

    html unordered list tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forbidden
    -0.07
     fullname
    -0.07
    likle
    -0.06
     stunt
    -0.06
    .notice
    -0.06
     interference
    -0.06
    minate
    -0.06
    lox
    -0.06
    biz
    -0.06
     bezpeč
    -0.06
    POSITIVE LOGITS
     вій
    0.07
     zboží
    0.07
     sph
    0.07
     Synd
    0.06
     fairly
    0.06
     Фран
    0.06
    (vo
    0.06
     виг
    0.06
     Prime
    0.06
    (ed
    0.06
    Act Density 0.015%

    No Known Activations