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

    Neuronpedia

    INDEX
    Explanations

    story excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    282
    -0.07
    .Are
    -0.07
    682
    -0.06
    RK
    -0.06
     feats
    -0.06
    281
    -0.06
    ň
    -0.06
    982
    -0.06
    맹
    -0.06
     beş
    -0.06
    POSITIVE LOGITS
    (strategy
    0.06
    <Key
    0.06
     इसक
    0.06
     absorbing
    0.06
     UF
    0.06
    BASEPATH
    0.06
    .deserialize
    0.06
    警
    0.06
    .sorted
    0.06
     Facing
    0.06
    Act Density 0.130%

    No Known Activations