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

    Neuronpedia

    INDEX
    Explanations

    about me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )!
    0.91
    :
    0.78
    /
    0.76
     пом
    0.75
     Schulz
    0.75
    !).
    0.73
     treat
    0.71
    ):
    0.71
    هداف
    0.70
     Arnaud
    0.69
    POSITIVE LOGITS
     hypothyroidism
    0.89
     বইটি
    0.84
     booked
    0.80
    ຫມ
    0.80
     violated
    0.79
    boleh
    0.78
     வேண்டிய
    0.78
    ရာ
    0.77
    Kerala
    0.77
    abama
    0.76
    Act Density 0.004%

    No Known Activations