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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蒜
    0.38
     Linux
    0.38
    enni
    0.37
     हुन
    0.37
     Roberta
    0.36
    zak
    0.36
     Ava
    0.36
    mm
    0.35
    sstream
    0.35
     Cobalt
    0.35
    POSITIVE LOGITS
    あとは
    0.41
     ploy
    0.40
     Determines
    0.39
     parochial
    0.39
     bible
    0.38
     generality
    0.38
     peremptory
    0.38
     believers
    0.38
     savvy
    0.38
    জি
    0.37
    Act Density 0.000%

    No Known Activations