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

    Neuronpedia

    INDEX
    Explanations

    pronoun-verb or subject-verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terrestrial
    0.50
     own
    0.49
     totality
    0.48
     tribal
    0.48
     pilgrimage
    0.48
     triads
    0.47
     terminology
    0.47
     dogma
    0.46
     nationalism
    0.45
     timelines
    0.45
    POSITIVE LOGITS
     করব
    0.50
    㑓
    0.48
    كما
    0.47
    位
    0.47
    涳
    0.46
    $.
    0.45
    迋
    0.45
     ଯ
    0.45
    Fetched
    0.45
    龺
    0.45
    Act Density 0.000%

    No Known Activations