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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Claim
    -0.08
     ноября
    -0.07
     bathtub
    -0.07
     TypeScript
    -0.07
     kỳ
    -0.06
     traits
    -0.06
     Cars
    -0.06
     mente
    -0.06
     projectile
    -0.06
     When
    -0.06
    POSITIVE LOGITS
    odies
    0.06
    エル
    0.06
    ً،
    0.06
     getItemCount
    0.06
    는지
    0.06
    шу
    0.06
    piel
    0.06
     हट
    0.06
    ้อน
    0.06
     živ
    0.06
    Act Density 0.038%

    No Known Activations