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

    Neuronpedia

    INDEX
    Explanations

    vision wards control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Những
    0.39
     digests
    0.35
    。
    0.34
    多様
    0.34
    hasOwnProperty
    0.33
    様々な
    0.33
    🥫
    0.33
    Привет
    0.33
    Какие
    0.32
    $.
    0.32
    POSITIVE LOGITS
     salud
    0.44
     swoim
    0.43
     della
    0.41
     своей
    0.40
     утром
    0.39
     entrare
    0.39
     управління
    0.39
     control
    0.39
     duelo
    0.39
     management
    0.38
    Act Density 0.253%

    No Known Activations