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

    Neuronpedia

    INDEX
    Explanations

    Find all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     эмоциона
    0.57
    irá
    0.51
    တို့ကို
    0.47
     neurotic
    0.47
     тя
    0.46
     manière
    0.45
     condimentum
    0.45
     profiling
    0.44
    皖
    0.44
     воздей
    0.44
    POSITIVE LOGITS
    ダイ
    0.54
    ASI
    0.52
    ک
    0.51
    د
    0.49
    target
    0.49
    Sebelum
    0.49
    dsb
    0.48
    Bas
    0.47
    v
    0.47
    dik
    0.46
    Act Density 0.000%

    No Known Activations