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

    Neuronpedia

    INDEX
    Explanations

    advice on etiquette and professional behavior in various social situations

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

    Immediately follows "if"

    np_acts-logits-general · gemini-2.0-flash

    punctuation and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.73
    گانه
    -0.62
    Demografia
    -0.62
     cref
    -0.62
    rungsseite
    -0.61
    DIPSETTING
    -0.61
    ñora
    -0.60
    ensement
    -0.59
    ArgumentParser
    -0.59
     naturali
    -0.59
    POSITIVE LOGITS
    \}\\
    0.89
     дописавши
    0.85
    \{\\
    0.79
    “
    0.67
    ‘
    0.67
    ]<<"
    0.65
    Enllaces
    0.63
    EnumMember
    0.63
    /***/
    0.63
    >>()
    0.63
    Act Density 0.296%

    No Known Activations