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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    Tokens followed by abbreviations

    np_acts-logits-general · gemini-2.0-flash

    N followed by abbreviations/names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.52
     صوتيه
    -0.49
     autorytatywna
    -0.48
    tagext
    -0.44
     Drapeau
    -0.44
    UserScript
    -0.43
    
    -0.43
     GoogleFonts
    -0.42
     itſelf
    -0.42
     Amethyst
    -0.42
    POSITIVE LOGITS
     NP
    1.09
     NM
    1.08
     NR
    1.07
     NU
    1.07
     Nicholas
    1.05
     NC
    1.05
     NS
    1.05
     Nelson
    1.04
     NF
    1.04
     Nicolas
    1.03
    Act Density 2.062%

    No Known Activations