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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (timeout
    -0.06
    (sound
    -0.06
     furn
    -0.06
    .spaceBetween
    -0.06
     curious
    -0.06
     viol
    -0.06
    _Init
    -0.06
    (second
    -0.06
    优势
    -0.06
    .example
    -0.06
    POSITIVE LOGITS
    AtA
    0.07
     QC
    0.07
    いつ
    0.07
    ruptions
    0.07
     získat
    0.07
    ervative
    0.07
    нике
    0.07
    скому
    0.06
     Lauderdale
    0.06
    .rename
    0.06
    Act Density 0.739%

    No Known Activations