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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provid
    -0.07
     anderen
    -0.07
     watching
    -0.07
     afternoon
    -0.07
    udev
    -0.07
    Them
    -0.07
    _PK
    -0.07
     вам
    -0.07
    ふ
    -0.06
    ाए
    -0.06
    POSITIVE LOGITS
     ・
    0.07
    1
    0.06
    标准
    0.06
     stressed
    0.06
    (normal
    0.06
    ۱
    0.06
     CTRL
    0.06
    ('?
    0.06
    .NewRequest
    0.06
    Verify
    0.06
    Act Density 0.027%

    No Known Activations