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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters associated with web addresses and HTML/XML components

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

    attribute name</xsl:attribute>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geſch
    -0.80
     beſch
    -0.79
    LookAnd
    -0.74
     queſta
    -0.72
    ſicht
    -0.72
     ſehr
    -0.69
     erſt
    -0.69
    ValueStyle
    -0.68
     мәкал
    -0.68
    +#+
    -0.67
    POSITIVE LOGITS
    complexContent
    0.94
     Wege
    0.31
     terceira
    0.27
     Sorge
    0.27
     sandalias
    0.27
     keduanya
    0.26
     Gelegenheit
    0.26
    gående
    0.26
     Freude
    0.26
     terpisah
    0.25
    Act Density 0.000%

    No Known Activations