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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ({});↵
    -0.08
     pq
    -0.07
    Target
    -0.07
    RunWith
    -0.06
    →
    -0.06
    10
    -0.06
    _for
    -0.06
     Approximately
    -0.06
    Of
    -0.06
    :])
    -0.06
    POSITIVE LOGITS
    oulos
    0.08
    porter
    0.07
     pari
    0.06
    .me
    0.06
     Nasıl
    0.06
     Miguel
    0.06
     samostat
    0.06
    How
    0.06
    dration
    0.06
     McInt
    0.06
    Act Density 0.138%

    No Known Activations