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

    Neuronpedia

    INDEX
    Explanations

    writing prompts and snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    야
    0.49
    ाराम
    0.48
    수
    0.47
    됐
    0.47
    afood
    0.46
    verbal
    0.46
    생
    0.44
    surfing
    0.44
    차
    0.44
    encoding
    0.44
    POSITIVE LOGITS
     öld
    0.48
     Ч
    0.47
     tipos
    0.45
     mercenaries
    0.45
    ຫ
    0.45
     êtres
    0.44
     காட்ட
    0.44
     излу
    0.43
     Amarillo
    0.43
     kills
    0.43
    Act Density 0.002%

    No Known Activations