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

    Neuronpedia

    INDEX
    Explanations

    enemy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Praze
    -0.07
     ساخت
    -0.07
     ráp
    -0.07
     cic
    -0.07
     vět
    -0.07
     Pfizer
    -0.06
     přik
    -0.06
    POSIT
    -0.06
    цвет
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     enemy
    0.10
     Enemy
    0.09
     Enemies
    0.09
     enemies
    0.08
    Enemies
    0.08
    key
    0.07
    _enemy
    0.07
     engine
    0.07
    inus
    0.06
     ≠
    0.06
    Act Density 0.007%

    No Known Activations