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

    Neuronpedia

    INDEX
    Explanations

    breakdown, definition, formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आत्मा
    0.47
    মিক্যাল
    0.46
    Chorus
    0.44
    ığımız
    0.44
    żej
    0.43
     toxins
    0.42
     iremos
    0.42
     knives
    0.41
     Chúng
    0.41
     Bow
    0.41
    POSITIVE LOGITS
     disbursements
    0.60
    date
    0.52
     endorsements
    0.49
     remittance
    0.49
    page
    0.49
     disbursement
    0.49
     appointing
    0.49
     date
    0.48
     cập
    0.47
    dateFormat
    0.47
    Act Density 0.009%

    No Known Activations