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

    Neuronpedia

    INDEX
    Explanations

    scrub your list, for char, white teeth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olok
    0.45
     committing
    0.44
    retryWrites
    0.40
     curios
    0.38
    arab
    0.37
    pec
    0.37
     uint
    0.37
     crumb
    0.37
     ec
    0.36
     pec
    0.36
    POSITIVE LOGITS
    ниях
    0.40
    Stock
    0.37
     школова
    0.37
    Extractor
    0.36
    flashdata
    0.36
    발
    0.36
     bhavanti
    0.36
    Vo
    0.35
    ddd
    0.35
    AVY
    0.35
    Act Density 0.000%

    No Known Activations