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

    Neuronpedia

    INDEX
    Explanations

    Q&A forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptrdiff
    -0.07
    implicitly
    -0.07
     않았
    -0.06
    Fetch
    -0.06
     accompanied
    -0.06
     contribution
    -0.06
    alık
    -0.06
     tímto
    -0.06
     подум
    -0.06
    ontent
    -0.06
    POSITIVE LOGITS
     mph
    0.07
    Ratio
    0.07
    (serial
    0.06
    .Profile
    0.06
     Surgery
    0.06
    анія
    0.06
     lp
    0.06
     Baltimore
    0.06
    _ann
    0.06
    (Buffer
    0.06
    Act Density 0.095%

    No Known Activations