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

    Neuronpedia

    INDEX
    Explanations

    go import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carcinogenic
    0.41
    上也
    0.39
     incipient
    0.39
    ﺎ
    0.38
     أيضًا
    0.37
     buttermilk
    0.37
     estar
    0.37
     aldehyde
    0.37
     syphilit
    0.36
     самом
    0.36
    POSITIVE LOGITS
    os
    0.45
    import
    0.44
    v
    0.44
    After
    0.43
    un
    0.41
     After
    0.41
    us
    0.40
    Data
    0.40
    i
    0.40
    As
    0.40
    Act Density 0.001%

    No Known Activations