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

    Neuronpedia

    INDEX
    Explanations

    content related to controversial or divisive statements

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

    Punctuation followed by a conjunction or qualifier

    np_acts-logits-general · gemini-2.0-flash

    end of sentence or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.38
     برانيه
    -0.34
    daging
    -0.33
     révélé
    -0.32
     pracov
    -0.31
    >("
    -0.30
     Insgesamt
    -0.28
     star
    -0.28
    ösungen
    -0.27
     règles
    -0.27
    POSITIVE LOGITS
     للاسماء
    0.69
    RegressionTest
    0.67
    tagHelperRunner
    0.63
     implying
    0.59
     kasarigan
    0.59
    ]=>
    0.59
    imply
    0.58
     implicitly
    0.56
    windowFixed
    0.56
    PreferredItem
    0.55
    Act Density 0.449%

    No Known Activations