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

    Neuronpedia

    INDEX
    Explanations

    satisfactory outcomes or responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ė
    1.08
    л
    1.05
     that
    0.94
    )
    0.93
    t
    0.91
    เ
    0.89
    ў
    0.87
     leggere
    0.87
    I
    0.87
    ค
    0.86
    POSITIVE LOGITS
    ᆷ
    0.94
    ي
    0.93
     satisfactory
    0.92
    <0xA5>
    0.88
     satisfactorily
    0.82
    <0xB2>
    0.80
    ಬ್ಬಿಣ
    0.80
    <0xA8>
    0.79
    но
    0.79
    ಿಣ
    0.79
    Act Density 0.001%

    No Known Activations