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

    Neuronpedia

    INDEX
    Explanations

    words starting with p

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excuses
    0.68
     deutsch
    0.67
     pend
    0.64
    ulously
    0.64
     conventionally
    0.63
     executor
    0.62
     collider
    0.61
     নেয়
    0.60
    췄
    0.60
     penn
    0.59
    POSITIVE LOGITS
    incipal
    0.74
    фай
    0.66
    ivate
    0.65
    nemonic
    0.63
    ofile
    0.62
    íncipe
    0.60
    род
    0.60
    atform
    0.60
    utth
    0.59
    壇
    0.57
    Act Density 0.134%

    No Known Activations