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

    Neuronpedia

    INDEX
    Explanations

    immediately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تجاوز
    -0.08
    Susp
    -0.08
    Cooldown
    -0.08
    Modifiers
    -0.08
     Tro
    -0.08
    pir
    -0.07
     מלח
    -0.07
     Mitchell
    -0.07
    貼
    -0.07
    Discard
    -0.07
    POSITIVE LOGITS
     ફોન
    0.09
     फोन
    0.09
     પ્રવ
    0.08
     skill
    0.08
     teléfono
    0.08
    akin
    0.07
     telefonisch
    0.07
     Linkedin
    0.07
     আলো
    0.07
     kommunik
    0.07
    Act Density 0.009%

    No Known Activations