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

    Neuronpedia

    INDEX
    Explanations

    inquiries about processes and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    how to ask a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſever
    -0.57
     ſch
    -0.56
     įsi
    -0.55
     ſtate
    -0.54
     saveiro
    -0.54
     ſta
    -0.54
     faſt
    -0.53
     démocr
    -0.53
     habitudes
    -0.53
     indígen
    -0.52
    POSITIVE LOGITS
    providedIn
    0.57
     ब्रेकडाउन
    0.55
    InitVars
    0.42
    enterOuterAlt
    0.41
    OGND
    0.41
    knex
    0.39
     shutil
    0.38
    󠁿
    0.38
    /*
    0.38
    رشف
    0.36
    Act Density 0.065%

    No Known Activations