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

    Neuronpedia

    INDEX
    Explanations

    Geography and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clasificación
    0.25
     목록
    0.24
     makeSound
    0.23
    梅里
    0.23
     发表
    0.23
     BELOW
    0.22
     BasicContainer
    0.22
     provoca
    0.22
    ير
    0.21
    分类
    0.21
    POSITIVE LOGITS
    ड्रो
    0.26
    gies
    0.25
     पुढे
    0.25
    liche
    0.25
     welt
    0.25
    norr
    0.24
     vzh
    0.24
    ête
    0.24
    kke
    0.24
    haften
    0.24
    Act Density 0.004%

    No Known Activations