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

    Neuronpedia

    INDEX
    Explanations

    themes related to democracy and participation

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

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.45
    aarrggbb
    -0.44
    ::_('
    -0.42
    <bos>
    -0.40
    $_['
    -0.39
     Obtenez
    -0.39
     gettin
    -0.37
    PreferredItem
    -0.36
    }{*}{
    -0.35
     nosso
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.55
    MessageOf
    0.53
     JpaRepository
    0.52
     HasFactory
    0.47
     somehow
    0.46
     utafitiHapana
    0.46
     indeed
    0.46
     converging
    0.45
     Babel
    0.45
     explí
    0.44
    Act Density 0.012%

    No Known Activations