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

    Neuronpedia

    INDEX
    Explanations

    building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вперед
    -0.07
     National
    -0.07
     cheating
    -0.07
    kaar
    -0.07
    พวก
    -0.06
    失败
    -0.06
    #!
    -0.06
    ेहर
    -0.06
     Walters
    -0.06
     AFTER
    -0.06
    POSITIVE LOGITS
    -Regular
    0.07
    ――――
    0.07
     lesbienne
    0.06
    _uniform
    0.06
    _buttons
    0.06
    ptions
    0.06
    _documento
    0.06
    brands
    0.06
    .website
    0.06
    math
    0.06
    Act Density 0.298%

    No Known Activations