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

    Neuronpedia

    INDEX
    Explanations

    oppositeley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    െടുത്ത
    0.89
     שה
    0.85
     poco
    0.85
    ឍ
    0.83
     చేరు
    0.82
     dalších
    0.78
     olabilir
    0.77
    の中でも
    0.77
    ्रेट
    0.77
    TAP
    0.76
    POSITIVE LOGITS
     extremes
    1.47
     polarity
    1.46
     extreme
    1.29
     poles
    1.27
     extremos
    1.26
     sides
    1.26
    polarity
    1.20
     pole
    1.19
     reaction
    1.15
    极端
    1.14
    Act Density 0.011%

    No Known Activations