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

    Neuronpedia

    INDEX
    Explanations

    references to file operations and system paths

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

    Characters followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    file paths and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nocache
    -0.48
     spur
    -0.46
     globos
    -0.45
     Hummel
    -0.44
     ligiloj
    -0.44
    sco
    -0.43
     JLabel
    -0.43
     scoping
    -0.42
     Caja
    -0.42
     customs
    -0.42
    POSITIVE LOGITS
    \
    0.91
     defStyleAttr
    0.70
    tvguidetime
    0.66
     "\
    0.62
    findpost
    0.61
    MENAFN
    0.60
     /\.
    0.59
     $\
    0.59
    (!__
    0.57
    ]='\
    0.57
    Act Density 0.166%

    No Known Activations