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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <t
    -0.07
     Kenny
    -0.07
     Qualität
    -0.07
    (de
    -0.06
     augmentation
    -0.06
    atisf
    -0.06
    _yaw
    -0.06
    ,↵↵
    -0.06
     这
    -0.06
    usty
    -0.06
    POSITIVE LOGITS
     scenery
    0.07
     Степ
    0.07
     PROCESS
    0.07
    _enter
    0.07
     że
    0.06
     scipy
    0.06
    iplinary
    0.06
    TEE
    0.06
    ControlEvents
    0.06
    .DefaultCellStyle
    0.06
    Act Density 0.022%

    No Known Activations