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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence and faith in various subjects

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

    trust, faith, or confidence

    np_acts-logits-general · gemini-2.0-flash

    confidence and trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.53
    таратура
    -0.41
    ngel
    -0.41
    Batis
    -0.40
    ajara
    -0.39
     Marais
    -0.39
     treas
    -0.38
     bush
    -0.38
    pired
    -0.38
    listes
    -0.38
    POSITIVE LOGITS
     trust
    0.93
     confidence
    0.88
     confident
    0.84
    confidence
    0.81
     Confidence
    0.80
     confianza
    0.80
     confiance
    0.79
     güven
    0.76
    trust
    0.75
    Confidence
    0.75
    Act Density 0.274%

    No Known Activations