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

    Neuronpedia

    INDEX
    Explanations

    faith and belief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ódigo
    0.55
     Бен
    0.50
    세요
    0.50
    ꯦ
    0.49
    ोले
    0.48
    liono
    0.47
    био
    0.47
    ⵥ
    0.47
    ፔ
    0.47
    sorting
    0.47
    POSITIVE LOGITS
     faith
    1.01
     Faith
    0.91
     belief
    0.89
     Belief
    0.84
     beliefs
    0.82
     believing
    0.79
     faiths
    0.77
     confidence
    0.75
     trust
    0.74
     Confidence
    0.73
    Act Density 0.026%

    No Known Activations