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

    Neuronpedia

    INDEX
    Explanations

    stories and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    隰
    0.48
    畯
    0.48
     خوات
    0.46
    Türk
    0.44
     anderen
    0.44
     innych
    0.44
    埛
    0.43
    埚
    0.43
    鋈
    0.42
    お
    0.42
    POSITIVE LOGITS
     characterized
    0.50
     lengthy
    0.50
     primarily
    0.46
     L
    0.44
     mainly
    0.43
     necessity
    0.42
     преимущественно
    0.41
     simply
    0.41
     unchanged
    0.41
    oliath
    0.41
    Act Density 0.008%

    No Known Activations