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

    Neuronpedia

    INDEX
    Explanations

    foreign language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geometrical
    0.29
     monotonic
    0.29
     subtraction
    0.29
     precipitation
    0.28
     foo
    0.28
     raster
    0.28
     checksum
    0.28
     operands
    0.28
     bitmap
    0.28
     leftovers
    0.27
    POSITIVE LOGITS
     кризи
    0.29
     estratégica
    0.28
     사회
    0.27
     persönlichen
    0.27
    anais
    0.26
     이야기를
    0.26
    Jamie
    0.26
    캠
    0.26
     ситуа
    0.26
     специалист
    0.26
    Act Density 3.572%

    No Known Activations