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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    content
    -0.07
     kvinn
    -0.07
    ioc
    -0.06
     عندما
    -0.06
     نزدیک
    -0.06
     Pre
    -0.06
     Ble
    -0.06
    (Be
    -0.06
    Hal
    -0.06
    modules
    -0.06
    POSITIVE LOGITS
    CAL
    0.08
     emlrt
    0.07
    .npy
    0.07
     MVP
    0.07
    (tex
    0.06
    .Metro
    0.06
     Notes
    0.06
     cams
    0.06
     payable
    0.06
    ウト
    0.06
    Act Density 0.076%

    No Known Activations