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

    Neuronpedia

    INDEX
    Explanations

    at a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     announcer
    0.68
     USS
    0.64
     episodios
    0.62
    usia
    0.58
     Kinect
    0.58
     episodes
    0.57
    琵
    0.56
    }}-\
    0.56
    xiety
    0.55
    ம்பரிய
    0.55
    POSITIVE LOGITS
     once
    1.04
     Once
    0.97
    Once
    0.91
    once
    0.88
     কথাই
    0.80
    FileUpload
    0.78
     любое
    0.78
     każde
    0.75
     একবার
    0.74
    HeaderText
    0.72
    Act Density 0.080%

    No Known Activations