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

    Neuronpedia

    INDEX
    Explanations

    overfitting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    글
    -0.10
    ucalyptus
    -0.09
     міжнарод
    -0.08
    暖
    -0.08
    ാര
    -0.08
    _HE
    -0.08
     Weiß
    -0.08
    觉
    -0.08
    国际
    -0.08
     restoran
    -0.08
    POSITIVE LOGITS
     perfectly
    0.09
     exact
    0.09
     EXACT
    0.09
     exactamente
    0.08
     flawlessly
    0.08
     tevreden
    0.08
    _exact
    0.08
    满意
    0.08
     даже
    0.08
     prácticamente
    0.08
    Act Density 0.006%

    No Known Activations