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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     סט
    0.47
    我们的
    0.46
    我們的
    0.45
    restrial
    0.45
    wd
    0.44
    kg
    0.43
    ljiv
    0.43
    remos
    0.43
     محبوب
    0.42
    摟
    0.42
    POSITIVE LOGITS
     Officer
    0.46
     Okay
    0.45
     inescap
    0.45
     François
    0.45
     Influ
    0.44
     influencia
    0.44
     Walters
    0.44
     todd
    0.43
     Hugh
    0.43
     francesa
    0.43
    Act Density 0.001%

    No Known Activations