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

    Neuronpedia

    INDEX
    Explanations

    ANI and current AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gın
    0.48
    it
    0.46
    raciones
    0.42
    contin
    0.42
    unique
    0.41
    helper
    0.41
    justice
    0.41
    i
    0.41
    Golden
    0.40
     dava
    0.40
    POSITIVE LOGITS
    <0x96>
    0.41
     ಅತ್ಯ
    0.40
     monitors
    0.40
     cultiv
    0.39
    czyn
    0.38
     Eritrea
    0.37
     Chakrab
    0.37
     এমন
    0.36
     хотя
    0.36
     인사
    0.36
    Act Density 0.000%

    No Known Activations