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

    Neuronpedia

    INDEX
    Explanations

    code indexing loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nécessité
    0.41
    मध्ये
    0.34
    Pourquoi
    0.32
     avulla
    0.32
    MyToolkit
    0.32
     შესახებ
    0.32
     vanligt
    0.30
     superfici
    0.29
     voorbeeld
    0.29
     egensk
    0.29
    POSITIVE LOGITS
     календар
    0.39
     almış
    0.37
    ngram
    0.36
     ήταν
    0.36
     parseInt
    0.35
     getAll
    0.35
     لیست
    0.35
    encode
    0.35
    OTAL
    0.34
    )+
    0.34
    Act Density 0.055%

    No Known Activations