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

    Neuronpedia

    INDEX
    Explanations

    code, abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Some
    -0.08
    _sim
    -0.08
    .S
    -0.08
     Sp
    -0.07
    [S
    -0.07
    _so
    -0.07
    ้าส
    -0.07
     دشمن
    -0.07
    (S
    -0.07
    -S
    -0.07
    POSITIVE LOGITS
     cryptography
    0.07
    _connected
    0.07
     illeg
    0.07
     лаборатор
    0.07
     лак
    0.06
     limb
    0.06
    (preg
    0.06
    Λ
    0.06
     lor
    0.06
     لف
    0.06
    Act Density 4.845%

    No Known Activations