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

    Neuronpedia

    INDEX
    Explanations

    OnPush OnSuccess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    owering
    0.42
     rounding
    0.40
    ito
    0.38
     riman
    0.38
    asion
    0.37
     cima
    0.37
    好看
    0.37
     blocked
    0.36
     leadership
    0.36
     IE
    0.36
    POSITIVE LOGITS
    वरून
    0.41
     বোঝ
    0.39
    மையும்
    0.39
    ças
    0.38
    OnChange
    0.38
    严格
    0.37
    谙
    0.37
     مطابق
    0.36
    公园
    0.36
     personajes
    0.36
    Act Density 0.000%

    No Known Activations