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

    Neuronpedia

    INDEX
    Explanations

    (ctx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    445
    -0.06
    all
    -0.06
    /features
    -0.06
    .list
    -0.06
     sequ
    -0.06
    ’all
    -0.06
    ันทร
    -0.06
    'label
    -0.06
    .writ
    -0.06
     metal
    -0.06
    POSITIVE LOGITS
    (ctx
    0.08
    .Italic
    0.07
     Colo
    0.07
    ctx
    0.07
     decided
    0.07
    Veter
    0.07
    _ctx
    0.07
     vaguely
    0.07
    _CODEC
    0.06
     Bangalore
    0.06
    Act Density 0.004%

    No Known Activations