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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and their authors

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

    Citations (e.g., et al.)

    np_acts-logits-general · gemini-2.0-flash

    et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynnwys
    -0.47
    aarrggbb
    -0.46
    erval
    -0.46
    )$/,
    -0.46
    équences
    -0.46
    waukee
    -0.44
    utenant
    -0.44
    chwitz
    -0.44
    umask
    -0.43
    WOL
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.87
     <<<<<<<<<<<<<<
    0.78
    principalTable
    0.70
     JADX
    0.64
    存于互联网档案馆
    0.64
     themselves
    0.62
    脚注の使い方
    0.61
    iestety
    0.59
     AssemblyCulture
    0.59
     JpaRepository
    0.58
    Act Density 0.670%

    No Known Activations