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

    Neuronpedia

    INDEX
    Explanations

    Python code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &&
    0.92
    "){
    0.87
    ")){
    0.83
    मेज
    0.73
    ])){
    0.72
    ))){
    0.72
    ')){
    0.72
    剩余
    0.71
     */
    0.71
    "]));
    0.70
    POSITIVE LOGITS
    ).__
    1.20
    .__
    1.12
    ().__
    0.97
    **.
    0.96
    **
    0.94
    यदि
    0.91
    **(
    0.89
    .**
    0.89
    ,)
    0.88
    [:]
    0.88
    Act Density 0.323%

    No Known Activations