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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    translation invariant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.46
    findpost
    -0.45
    }])
    -0.40
     ratified
    -0.37
    ++)
    -0.37
    hom
    -0.36
     counting
    -0.35
     flagged
    -0.35
    AccessorTable
    -0.34
    Zusammenfassung
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.55
    adaptiveStyles
    0.50
     دیکھیے
    0.49
    XmlEnum
    0.44
     funciones
    0.43
    iální
    0.43
    хьтан
    0.43
     جغرافيا
    0.42
    astéroïdes
    0.42
     Functions
    0.41
    Act Density 0.385%

    No Known Activations