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

    Neuronpedia

    INDEX
    Explanations

    the followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    0.40
    lc
    0.39
    nThe
    0.36
    The
    0.35
     שת
    0.34
    STE
    0.34
     singleRun
    0.34
    rta
    0.33
    t
    0.33
    生地
    0.33
    POSITIVE LOGITS
     tại
    0.39
     på
    0.36
    ेक्स
    0.36
     než
    0.36
     får
    0.36
     lekker
    0.36
     ณ
    0.35
     än
    0.34
     jacket
    0.33
    ոն
    0.33
    Act Density 0.000%

    No Known Activations