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

    Neuronpedia

    INDEX
    Explanations

    texture and spatial image features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moseley
    -0.82
    チェン
    -0.73
     склада
    -0.73
    藜
    -0.71
    annister
    -0.71
     Mose
    -0.71
     Nguyễn
    -0.71
     золота
    -0.71
    Isaac
    -0.69
     blinked
    -0.69
    POSITIVE LOGITS
     texture
    1.32
    texture
    1.09
     Texture
    1.09
     textures
    1.09
    Texture
    0.98
     gray
    0.93
    textures
    0.92
     Textures
    0.90
     texturas
    0.87
     Structural
    0.86
    Act Density 0.030%

    No Known Activations