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

    Neuronpedia

    INDEX
    Explanations

    Aristotelian principles and indifferents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ríg
    0.82
     Hermes
    0.79
     Rosetta
    0.77
     ancient
    0.76
     Ancient
    0.74
     répand
    0.71
     Oracle
    0.71
     biblical
    0.71
     faithfully
    0.70
     Nederlandse
    0.70
    POSITIVE LOGITS
     pain
    0.85
    Injury
    0.74
     ঘন্ট
    0.69
    pain
    0.68
    Pain
    0.67
     extremity
    0.66
    posite
    0.66
     coaction
    0.66
     Pain
    0.66
     pains
    0.65
    Act Density 0.011%

    No Known Activations