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

    Neuronpedia

    INDEX
    Explanations

    health advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OutputStream
    -0.07
     bush
    -0.07
     Implements
    -0.07
     decreasing
    -0.06
     buiten
    -0.06
     pill
    -0.06
    -negative
    -0.06
     StringComparison
    -0.06
    .Actor
    -0.06
    _'
    -0.06
    POSITIVE LOGITS
     Lav
    0.06
    aley
    0.06
    Sadly
    0.06
    aln
    0.06
    層
    0.06
    veyor
    0.06
    xBA
    0.06
     TSA
    0.06
     favored
    0.06
    ensual
    0.06
    Act Density 0.053%

    No Known Activations