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

    Neuronpedia

    INDEX
    Explanations

    paragraphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.92
     nakalista
    -0.91
     وتسجيلات
    -0.91
    expandindo
    -0.86
    AsUp
    -0.84
    脚注の使い方
    -0.82
    spot
    -0.81
     doInBackground
    -0.81
    bewerken
    -0.80
    shmi
    -0.78
    POSITIVE LOGITS
    .
    0.50
     around
    0.47
    ,
    0.47
     of
    0.47
     to
    0.46
     when
    0.46
     near
    0.46
     like
    0.45
     based
    0.44
     both
    0.44
    Act Density 1.589%

    No Known Activations