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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leriyle
    -0.07
     shuts
    -0.07
     Haus
    -0.07
    ädchen
    -0.07
     bunların
    -0.06
    тап
    -0.06
    álie
    -0.06
    ナル
    -0.06
    süz
    -0.06
    isnan
    -0.06
    POSITIVE LOGITS
    ptest
    0.07
    .ST
    0.07
    .tbl
    0.06
    311
    0.06
    getDoctrine
    0.06
    _shape
    0.06
    .Input
    0.06
    IOD
    0.06
    gregator
    0.06
     claim
    0.06
    Act Density 0.000%

    No Known Activations