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

    Neuronpedia

    INDEX
    Explanations

    /library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imu
    -0.07
    .Tr
    -0.07
    _END
    -0.07
    頭
    -0.07
    ieve
    -0.06
    оне
    -0.06
    องจาก
    -0.06
    eras
    -0.06
    jab
    -0.06
    Impossible
    -0.06
    POSITIVE LOGITS
    /library
    0.08
    warts
    0.07
     qu
    0.07
     rely
    0.06
     `"
    0.06
     clash
    0.06
    /Object
    0.06
    ‐
    0.06
    _SUR
    0.06
    .Adapter
    0.06
    Act Density 0.000%

    No Known Activations