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

    Neuronpedia

    INDEX
    Explanations

    ways to list information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GB
    0.50
    のではないでしょうか
    0.46
     adhipp
    0.44
    Colombo
    0.44
     basePath
    0.42
    SSA
    0.42
    SR
    0.42
    NSW
    0.41
    NDC
    0.41
    ایط
    0.41
    POSITIVE LOGITS
    ację
    0.46
    azione
    0.46
    lardan
    0.46
    atorul
    0.45
     bloque
    0.44
    手动
    0.44
     durch
    0.44
    atore
    0.43
    uje
    0.43
    س
    0.42
    Act Density 0.042%

    No Known Activations