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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (builder
    -0.07
    ↵    ↵    ↵
    -0.06
    994
    -0.06
    eprom
    -0.06
    キー
    -0.06
     крови
    -0.06
     ROT
    -0.06
    ấu
    -0.06
    ょう
    -0.06
     shredded
    -0.06
    POSITIVE LOGITS
     Mounted
    0.07
    imir
    0.07
    Datos
    0.06
    umuz
    0.06
    .hasOwnProperty
    0.06
     سكان
    0.06
    .velocity
    0.06
    前の
    0.06
    坐在
    0.06
    .jobs
    0.06
    Act Density 0.137%

    No Known Activations