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

    Neuronpedia

    INDEX
    Explanations

    UC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Everyone
    -0.07
     overtime
    -0.07
     pán
    -0.06
     incorpor
    -0.06
     Sir
    -0.06
     butt
    -0.06
    น
    -0.06
     rng
    -0.06
    <(
    -0.06
     alarmed
    -0.06
    POSITIVE LOGITS
    _clusters
    0.07
     RuntimeMethod
    0.07
    istica
    0.07
    .Rem
    0.07
    sanitize
    0.07
    uars
    0.07
    IGATION
    0.06
    xBA
    0.06
     provincia
    0.06
     strtolower
    0.06
    Act Density 0.012%

    No Known Activations