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

    Neuronpedia

    INDEX
    Explanations

    ratio of similar shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     συν
    -0.08
     permanece
    -0.07
     BFS
    -0.07
     discomfort
    -0.07
     ук
    -0.07
    hot
    -0.07
    manageable
    -0.07
    Clickable
    -0.07
    زار
    -0.07
    click
    -0.07
    POSITIVE LOGITS
     scaling
    0.13
     Scaling
    0.12
    Scaling
    0.11
    caling
    0.10
    .scale
    0.09
    quared
    0.09
    _scal
    0.08
    比例
    0.08
     scaled
    0.08
     resized
    0.08
    Act Density 0.044%

    No Known Activations