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

    Neuronpedia

    INDEX
    Explanations

    atches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wide
    -0.07
     shelves
    -0.07
    ์ล
    -0.07
    رة
    -0.06
     buried
    -0.06
     attractive
    -0.06
     سابق
    -0.06
     Wool
    -0.06
     alloy
    -0.06
    واره
    -0.06
    POSITIVE LOGITS
     دف
    0.06
    龄
    0.06
    (example
    0.06
    เข
    0.06
    .fre
    0.06
     quatre
    0.06
     技
    0.06
    (newState
    0.06
    invalidate
    0.06
    laws
    0.06
    Act Density 0.000%

    No Known Activations