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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𫚕
    -0.07
    صح
    -0.07
    wish
    -0.07
    樱
    -0.06
    转
    -0.06
     favor
    -0.06
    tığ
    -0.06
    axed
    -0.06
    part
    -0.06
    mask
    -0.06
    POSITIVE LOGITS
    徂
    0.07
     metres
    0.07
     brick
    0.07
     filthy
    0.07
    $fields
    0.07
    [counter
    0.07
    (vehicle
    0.07
    actics
    0.07
    edics
    0.07
    כביש
    0.07
    Act Density 0.028%

    No Known Activations