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

    Neuronpedia

    INDEX
    Explanations

    terms related to collective actions or group activities

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

    add to list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.52
    󠁴
    -0.44
     datastore
    -0.43
    noscript
    -0.43
    ฟ้า
    -0.42
    requestId
    -0.41
    reactivex
    -0.41
     Nachfrage
    -0.41
     here
    -0.40
     covariance
    -0.40
    POSITIVE LOGITS
    将
    0.82
    把
    0.77
     将
    0.73
    將
    0.71
     將
    0.65
    并将
    0.61
     把
    0.61
    });*/
    0.56
    要把
    0.53
    将她
    0.53
    Act Density 0.002%

    No Known Activations