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

    Neuronpedia

    INDEX
    Explanations

    terms related to options, flexibility, and inclusivity in various contexts

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

    lists, conjunctions, and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.63
     незавершена
    -0.63
    AnchorStyles
    -0.63
     myſelf
    -0.60
     itſelf
    -0.59
     ब्रेकडाउन
    -0.58
    Portail
    -0.58
    niſſe
    -0.57
     utafitiHapana
    -0.57
    IndentedString
    -0.56
    POSITIVE LOGITS
    writeObject
    0.30
     sekal
    0.30
     力
    0.29
    une
    0.29
    vorg
    0.29
     even
    0.29
     prome
    0.28
     Tom
    0.28
     Prom
    0.28
    pyplot
    0.28
    Act Density 0.029%

    No Known Activations