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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    782
    -0.07
     PROM
    -0.07
    .nlm
    -0.06
     pv
    -0.06
     Slug
    -0.06
    _COMPAT
    -0.06
     NSURL
    -0.06
    .de
    -0.06
    $L
    -0.06
    _ROT
    -0.06
    POSITIVE LOGITS
     tavern
    0.07
    BV
    0.06
     Shelter
    0.06
    -button
    0.06
    ็กหญ
    0.06
    :::::|
    0.06
    씀
    0.06
    leşme
    0.06
    enville
    0.06
    аза
    0.06
    Act Density 0.017%

    No Known Activations