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

    Neuronpedia

    INDEX
    Explanations

    NATO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pai
    -0.08
    ාවේ
    -0.08
    äinen
    -0.08
    לית
    -0.08
     mają
    -0.08
     Maj
    -0.08
    тыг
    -0.08
     сярэд
    -0.07
     Economy
    -0.07
     (;
    -0.07
    POSITIVE LOGITS
     коллектив
    0.10
     NATO
    0.08
     alerts
    0.08
     weapons
    0.08
     algorit
    0.08
     guaranteeing
    0.07
    stretch
    0.07
     armour
    0.07
     SIGNAL
    0.07
     exclusion
    0.07
    Act Density 0.007%

    No Known Activations