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

    Neuronpedia

    INDEX
    Explanations

    tech, place, or version identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     برای
    0.46
     sambil
    0.39
    亗
    0.39
     ከዚያ
    0.37
     nhưng
    0.37
    omitempty
    0.37
    就行
    0.37
     spores
    0.36
     tại
    0.36
     canv
    0.35
    POSITIVE LOGITS
    版的
    0.56
    における
    0.53
    においては
    0.49
    においても
    0.45
    5
    0.44
    6
    0.43
     lacks
    0.43
    缺乏
    0.42
    punyai
    0.41
    GC
    0.40
    Act Density 0.067%

    No Known Activations