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

    Neuronpedia

    INDEX
    Explanations

    Faiss Index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decently
    0.43
     perfección
    0.41
     motorcycles
    0.41
     terceiro
    0.41
    ड़ा
    0.40
    {\'
    0.39
     motorcycle
    0.39
    म
    0.38
     \'
    0.38
     Jacoby
    0.38
    POSITIVE LOGITS
    uenti
    0.40
    筲
    0.39
    iconfont
    0.39
    itetty
    0.38
    必然
    0.38
     미술
    0.38
    สัมพันธ์
    0.38
    界面
    0.37
     suic
    0.37
    itet
    0.37
    Act Density 0.027%

    No Known Activations