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

    Neuronpedia

    INDEX
    Explanations

    elements of social justice issues relating to race and accountability

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

    following auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.08
     myſelf
    -0.91
     ―――――
    -0.87
    invokeLater
    -0.87
     raiſ
    -0.85
    setVerticalGroup
    -0.85
     Pingback
    -0.83
    Espèce
    -0.79
    DeleteBehavior
    -0.78
     ་་
    -0.77
    POSITIVE LOGITS
    !
    1.66
    ;
    1.42
    .
    1.31
    ?
    1.26
    !!
    1.14
     but
    1.07
     because
    1.07
    !,
    1.02
    ;
    1.02
    !!!
    1.00
    Act Density 0.760%

    No Known Activations