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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .refs
    -0.07
     pornofilm
    -0.06
    .assertj
    -0.06
    羅
    -0.06
    决
    -0.06
     ст
    -0.06
    /renderer
    -0.06
    vocab
    -0.06
     PCI
    -0.06
    (h
    -0.06
    POSITIVE LOGITS
     haciendo
    0.08
     regeneration
    0.06
    _NOW
    0.06
    接
    0.06
     Agile
    0.06
    ğit
    0.06
    cao
    0.06
    ennes
    0.06
    FUL
    0.06
     eql
    0.06
    Act Density 0.025%

    No Known Activations