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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or conclusions

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

    introduction of further details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jspb
    -0.67
     CommandType
    -0.50
    jspb
    -0.49
    CommandType
    -0.48
     مشين
    -0.48
    twimg
    -0.47
     snippetHide
    -0.46
     zijne
    -0.45
     geda
    -0.45
     */;
    -0.45
    POSITIVE LOGITS
     Notably
    0.46
    󠁴
    0.45
    anmoins
    0.43
     Nevertheless
    0.41
    inaison
    0.41
     revel
    0.41
    észetes
    0.40
     Furthermore
    0.40
     RESTRICT
    0.40
    另一方面
    0.39
    Act Density 0.200%

    No Known Activations