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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences or lists

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

    Followed by hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    commas and byte sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Her
    -0.58
     $#
    -0.57
     Ter
    -0.56
    ’
    -0.55
    ModelAdmin
    -0.52
     היש
    -0.52
    ?
    -0.52
    -
    -0.51
     In
    -0.50
     Mol
    -0.50
    POSITIVE LOGITS
     Roskov
    1.07
     صوتيه
    0.96
    +#+#
    0.95
    ,,,,
    0.91
     poffible
    0.90
    IntoConstraints
    0.89
    ,-,
    0.89
     חיצוניים
    0.86
    [],
    0.86
     purpoſe
    0.85
    Act Density 0.240%

    No Known Activations