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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating involvement in actions or performances

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

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     priorité
    -0.45
     melh
    -0.39
    priority
    -0.38
     priority
    -0.34
     simple
    -0.34
     visibilité
    -0.32
     Alltag
    -0.32
     prioridad
    -0.31
     agujas
    -0.31
     misura
    -0.31
    POSITIVE LOGITS
    AnchorTagHelper
    0.65
    devamını
    0.61
     surla
    0.59
     Efq
    0.58
     الحره
    0.57
    +#+
    0.57
     localObject
    0.57
    himovic
    0.57
     Anſ
    0.57
    تقاوى
    0.56
    Act Density 0.044%

    No Known Activations