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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lord
    -0.09
     sift
    -0.08
    磕
    -0.07
     adult
    -0.07
    寺
    -0.07
    방
    -0.07
     fractured
    -0.07
    沦
    -0.07
     Bed
    -0.07
    bine
    -0.06
    POSITIVE LOGITS
    NullOr
    0.07
    évén
    0.07
     uwagę
    0.07
    مرة
    0.07
    uebas
    0.07
     interval
    0.06
     tuyệt
    0.06
     quà
    0.06
    けて
    0.06
    newInstance
    0.06
    Act Density 0.001%

    No Known Activations