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

    Neuronpedia

    INDEX
    Explanations

    word starting with d or D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ocult
    0.41
     främ
    0.37
     확보
    0.35
     außerhalb
    0.33
    astung
    0.33
    აც
    0.33
    বহ
    0.33
    assed
    0.32
    珬
    0.32
     criticized
    0.32
    POSITIVE LOGITS
     D
    1.09
    D
    0.83
    ifferentiating
    0.66
    ungeons
    0.65
    d
    0.64
    ifferentiated
    0.64
    ENSITY
    0.61
    andelions
    0.59
    andelion
    0.58
    actyl
    0.57
    Act Density 0.033%

    No Known Activations