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

    Neuronpedia

    INDEX
    Explanations

    every encounter, shadow, or step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guilt
    0.48
     (
    0.46
     adapting
    0.44
    ci
    0.44
     helpful
    0.44
     favored
    0.43
     i
    0.43
     a
    0.42
     guer
    0.42
     guessed
    0.41
    POSITIVE LOGITS
    hyth
    0.46
    విత
    0.45
    糖尿病
    0.45
    ケース
    0.43
    トラ
    0.42
     sillonné
    0.42
    ulsions
    0.41
    ণিত
    0.41
     उन्ह
    0.41
    SPR
    0.41
    Act Density 0.009%

    No Known Activations