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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations

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

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.47
     urmă
    -0.41
     sienta
    -0.40
     étoient
    -0.40
     feroit
    -0.39
     avoient
    -0.38
     avesse
    -0.38
     enseña
    -0.38
     ponga
    -0.37
    merkt
    -0.36
    POSITIVE LOGITS
     صوتيه
    0.71
    AndEndTag
    0.68
    RenderAtEndOf
    0.67
    resave
    0.58
    esModule
    0.55
    StandardCharsets
    0.53
    tagHelperRunner
    0.52
    formik
    0.51
    zzleHttp
    0.50
     ویکی‌پدیای
    0.50
    Act Density 0.117%

    No Known Activations