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

    Neuronpedia

    INDEX
    Explanations

    assertions of certainty or claims of inevitability

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

    certainty and guarantees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.40
     húmedo
    -0.39
     leña
    -0.34
    ovatel
    -0.34
     nuvem
    -0.34
     Übergang
    -0.34
     pierna
    -0.33
     Tropfen
    -0.33
     benih
    -0.33
     alfombra
    -0.33
    POSITIVE LOGITS
    certainty
    0.71
     certainty
    0.68
    setVerticalGroup
    0.66
     certitude
    0.61
    anteed
    0.61
     guaranteed
    0.59
    Guaranteed
    0.59
    Obvious
    0.59
     sure
    0.58
     Guaranteed
    0.57
    Act Density 0.060%

    No Known Activations