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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    Fractions or expressions with "j" and "r"

    np_acts-logits-general · gemini-2.0-flash

    mathematical variables (+,-, etc.)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //:
    -0.54
    照
    -0.47
    Г
    -0.43
     عم
    -0.43
     Mag
    -0.42
    }^{*}\
    -0.42
    fa
    -0.42
    허
    -0.42
    —
    -0.41
    稀
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.93
    adaptiveStyles
    0.90
    OGND
    0.77
     AssemblyVersion
    0.75
     HttpNotFound
    0.74
    ."));
    0.73
     Italijanski
    0.72
    expandindo
    0.71
     صوتيه
    0.70
    intios
    0.69
    Act Density 1.291%

    No Known Activations