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

    Neuronpedia

    INDEX
    Explanations

    experience reporting, more favorable, no escape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    0.52
    يده
    0.50
    ੰਜ
    0.49
    encia
    0.43
    imento
    0.43
    куляр
    0.43
    은
    0.43
     Term
    0.42
    灸
    0.42
    完了
    0.42
    POSITIVE LOGITS
    Qw
    0.57
    Mb
    0.54
    Cosine
    0.49
    CLES
    0.46
    CharCode
    0.46
    Baked
    0.45
    queued
    0.45
    Allocation
    0.44
    Authority
    0.44
    Slate
    0.44
    Act Density 0.001%

    No Known Activations