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

    Neuronpedia

    INDEX
    Explanations

    statistics and details related to legal rulings, particularly concerning race and justified actions

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

    Past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    verb + outcome or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.86
    。
    -0.66
    $.
    -0.62
    %.
    -0.58
    }$.
    -0.53
    ."""
    -0.53
    ."
    -0.52
    .
    -0.51
    ).
    -0.51
     \%$.
    -0.50
    POSITIVE LOGITS
     Paglinawan
    0.82
    脚注の使い方
    0.70
    NameInMap
    0.70
    SourceChecksum
    0.68
     CWE
    0.68
    исленность
    0.66
     през
    0.64
     yesterday
    0.63
    WithIOException
    0.63
     ayer
    0.62
    Act Density 0.645%

    No Known Activations