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

    Neuronpedia

    INDEX
    Explanations

    propose or proposal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    0.76
    ро
    0.74
     D
    0.64
    п
    0.63
    ط
    0.63
     Ch
    0.62
    я
    0.61
    懼
    0.60
    д
    0.60
    ي
    0.60
    POSITIVE LOGITS
     proposals
    0.87
     proposta
    0.86
    提案
    0.84
     proposed
    0.77
    Proposed
    0.77
     propuesta
    0.75
     proposes
    0.73
     propos
    0.73
    Proposal
    0.73
    ﺍ
    0.72
    Act Density 0.015%

    No Known Activations