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

    Neuronpedia

    INDEX
    Explanations

    Game stats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappearance
    -0.07
    ).↵↵
    -0.07
     Charg
    -0.07
     Clicking
    -0.07
    NYSE
    -0.07
    Opinion
    -0.07
     cí
    -0.07
     Seating
    -0.07
    _EXPECT
    -0.07
    !).↵↵
    -0.06
    POSITIVE LOGITS
     कमज
    0.09
     competencies
    0.09
     proficiency
    0.09
     juga
    0.08
    lero
    0.08
     pretrained
    0.08
     компет
    0.08
     affin
    0.08
     complemento
    0.08
    856
    0.08
    Act Density 0.005%

    No Known Activations