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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pasadena
    -0.07
    acular
    -0.07
     AREA
    -0.07
    .protocol
    -0.06
    _sur
    -0.06
    루
    -0.06
    程序
    -0.06
    Coverage
    -0.06
    Degrees
    -0.06
    sik
    -0.06
    POSITIVE LOGITS
    (Bundle
    0.07
    _Act
    0.07
    /Observable
    0.06
    .EditText
    0.06
    两人
    0.06
    یمت
    0.06
     حرفه
    0.06
    .News
    0.06
    [@
    0.06
     ◆
    0.06
    Act Density 0.104%

    No Known Activations