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

    Neuronpedia

    INDEX
    Explanations

    first step to acknowledging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thc
    0.95
    ht
    0.95
    xy
    0.93
     It
    0.90
    igh
    0.87
    hm
    0.86
    hangi
    0.86
    hty
    0.86
    ান্তি
    0.86
    oth
    0.86
    POSITIVE LOGITS
     metagen
    1.40
    гур
    1.38
     cerámica
    1.36
     సన్ని
    1.31
    高端
    1.30
     రాజ్యం
    1.29
     precio
    1.29
     presos
    1.27
     remaster
    1.26
     کرمان
    1.26
    Act Density 0.003%

    No Known Activations