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

    Neuronpedia

    INDEX
    Explanations

    technical subjects and proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಾಧ
    -0.08
     addict
    -0.08
    /prom
    -0.08
    /img
    -0.08
    одерж
    -0.07
    Addon
    -0.07
    lagen
    -0.07
     addicts
    -0.07
    पूर्ण
    -0.07
     inspirational
    -0.07
    POSITIVE LOGITS
     Kry
    0.09
     Gay
    0.08
     Johannes
    0.08
     Judaism
    0.07
    0.07
     Impro
    0.07
     اهمیت
    0.07
     높
    0.07
     deft
    0.07
     שפ
    0.07
    Act Density 0.000%
    No Known Activations