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

    Neuronpedia

    INDEX
    Explanations

    http or https links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Oct
    0.83
    Touching
    0.82
     प्रोत्साहित
    0.79
    gatsby
    0.77
    iye
    0.76
    lovepoetry
    0.76
    Biography
    0.74
    ">*
    0.73
    bakan
    0.73
    sure
    0.73
    POSITIVE LOGITS
     into
    0.84
     אבל
    0.83
     but
    0.77
     ugl
    0.77
    ということ
    0.75
     డ
    0.73
    šk
    0.73
     Sensors
    0.71
     collided
    0.71
     colliding
    0.71
    Act Density 0.028%

    No Known Activations