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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack of certainty or denial regarding business dealings

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

    "no" followed by a reason/explanation

    np_acts-logits-general · gemini-2.0-flash

    expressing doubt or lack of knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     définiti
    -0.60
     lumineux
    -0.59
     vôtre
    -0.59
     réfrig
    -0.59
     nuages
    -0.57
     sfeer
    -0.57
     fatica
    -0.57
     podendo
    -0.56
    Vidite
    -0.56
    jalá
    -0.56
    POSITIVE LOGITS
     access
    0.92
     aspirations
    0.82
     ambitions
    0.82
     experience
    0.76
     knowledge
    0.76
     interest
    0.75
    access
    0.74
     interests
    0.73
     plans
    0.72
     intentions
    0.72
    Act Density 0.343%

    No Known Activations