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

    Neuronpedia

    INDEX
    Explanations

    GPU specs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ate
    1.27
    az
    1.27
    ित
    1.09
    CT
    0.95
     Search
    0.95
     Negotiation
    0.94
     Stream
    0.93
     Stack
    0.92
    ang
    0.91
    ুর
    0.91
    POSITIVE LOGITS
     journée
    1.24
    澳門
    1.23
    新加坡
    1.15
     今年
    1.14
    нном
    1.14
    GPUs
    1.13
     Nvidia
    1.12
    mouseX
    1.12
     cottura
    1.11
    我
    1.10
    Act Density 0.372%

    No Known Activations