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

    Neuronpedia

    INDEX
    Explanations

    NON

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卒
    -0.07
    ampton
    -0.06
     ніби
    -0.06
     MF
    -0.06
    Anth
    -0.06
     ks
    -0.06
     السعود
    -0.06
    oric
    -0.06
    redd
    -0.05
    amodel
    -0.05
    POSITIVE LOGITS
    atter
    0.07
    air
    0.07
     hm
    0.07
    ayer
    0.06
    /manual
    0.06
    ui
    0.06
    рать
    0.06
    ！↵
    0.06
    Modifier
    0.06
    [level
    0.06
    Act Density 0.000%

    No Known Activations