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

    Neuronpedia

    INDEX
    Explanations

    language that conveys urgency or importance

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

    phrases indicating the need for improvement or change

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

    Climb those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mapStateToProps
    -0.67
    存于互联网档案馆
    -0.65
    __':
    -0.64
    SharedCtor
    -0.61
    })()
    -0.60
    __":
    -0.60
    xffffff
    -0.59
    这一点
    -0.55
     therefor
    -0.54
    SpringRunner
    -0.54
    POSITIVE LOGITS
     those
    2.19
    those
    1.99
    Those
    1.88
     Those
    1.83
     THOSE
    1.70
     daquele
    1.61
     aquele
    1.61
     aquela
    1.61
     quegli
    1.56
    quela
    1.45
    Act Density 0.218%

    No Known Activations