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

    Neuronpedia

    INDEX
    Explanations

    background script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ＊
    0.42
    ohon
    0.41
     Localization
    0.40
    _______________
    0.40
    来看看
    0.40
     Vì
    0.39
     Rename
    0.39
     सुप्रभात
    0.38
     Validación
    0.38
     इंग्लिश
    0.38
    POSITIVE LOGITS
     պատ
    0.40
    fant
    0.40
    charCodeAt
    0.39
     full
    0.38
     fasci
    0.38
     upside
    0.38
     cargas
    0.38
    триму
    0.38
     ná
    0.38
     protr
    0.38
    Act Density 0.000%

    No Known Activations