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

    Neuronpedia

    INDEX
    Explanations

    the landscape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neurotic
    0.37
     olun
    0.37
    getBoolean
    0.36
    rawn
    0.36
    trombone
    0.35
     doloribus
    0.35
     کھانے
    0.35
     অনুসন্ধ
    0.35
     받고
    0.35
     உள
    0.35
    POSITIVE LOGITS
    asn
    0.49
    آن
    0.47
    Ass
    0.45
    Рабо
    0.41
    마
    0.39
     रिज
    0.38
     поч
    0.38
     आस
    0.37
     assignments
    0.37
    グレ
    0.37
    Act Density 0.000%

    No Known Activations