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

    Neuronpedia

    INDEX
    Explanations

    variant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    かもしれません
    0.38
     zuz
    0.38
    뺄
    0.38
     خال
    0.37
     addItem
    0.37
     الزام
    0.37
     sy
    0.37
     빠
    0.37
     hobbies
    0.36
    ဖြ
    0.36
    POSITIVE LOGITS
     variation
    0.58
     variación
    0.55
    Variation
    0.54
    variation
    0.52
     Variation
    0.47
    Vari
    0.46
     variations
    0.45
     varient
    0.44
     fórmula
    0.44
     variant
    0.44
    Act Density 0.000%

    No Known Activations