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

    Neuronpedia

    INDEX
    Explanations

    references to specific days or moments event in time

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

    first day of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     culoare
    -0.57
     picioare
    -0.50
     oscuridad
    -0.50
     finanzas
    -0.49
     templado
    -0.49
     húmedo
    -0.48
     høy
    -0.48
     doméstico
    -0.47
     ochrony
    -0.47
     comigo
    -0.47
    POSITIVE LOGITS
    第一天
    0.65
     يتيمه
    0.59
     Chwiliwch
    0.57
     intStringLen
    0.55
    httphttps
    0.54
     reaper
    0.52
     Arrival
    0.50
    ThroughAttribute
    0.49
    SFD
    0.49
    structor
    0.48
    Act Density 0.009%

    No Known Activations