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

    Neuronpedia

    INDEX
    Explanations

    Contraception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIZE
    -0.07
     menace
    -0.07
    ition
    -0.06
     VALUES
    -0.06
    orphic
    -0.06
    tracker
    -0.06
    GROUND
    -0.06
    Army
    -0.06
    破
    -0.06
    ({_
    -0.06
    POSITIVE LOGITS
    联合
    0.07
    —you
    0.06
     Beverage
    0.06
     پیچ
    0.06
     перек
    0.06
     görev
    0.06
    베
    0.06
     Kelly
    0.06
    lander
    0.06
     proportional
    0.06
    Act Density 0.018%

    No Known Activations