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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cobra
    -0.08
     killing
    -0.08
     watching
    -0.08
     pretending
    -0.07
    rol
    -0.07
     whipping
    -0.07
    Cull
    -0.07
     Watching
    -0.07
    ्ट्र
    -0.07
     nal
    -0.07
    POSITIVE LOGITS
     informal
    0.14
     casual
    0.11
     допуска
    0.10
     honn
    0.09
     inappropriate
    0.09
     casually
    0.09
     friendliness
    0.09
     chaleure
    0.08
     personable
    0.08
     voire
    0.08
    Act Density 0.027%

    No Known Activations