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

    Neuronpedia

    INDEX
    Explanations

    dynamically generated files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.55
    }{
    0.53
    DATE
    0.46
    schutz
    0.46
     powerhouse
    0.44
     conducting
    0.43
    ,
    0.43
     AND
    0.43
    =
    0.42
    URL
    0.42
    POSITIVE LOGITS
    发现
    0.51
     Perimeter
    0.48
     Fractals
    0.48
     Cameras
    0.47
    cimentos
    0.46
     Mudah
    0.45
    Cameras
    0.44
    Physics
    0.44
     Polymers
    0.44
    设定
    0.43
    Act Density 0.006%

    No Known Activations