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

    Neuronpedia

    INDEX
    Explanations

    code blocks and JSON structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grass
    0.39
    Grass
    0.36
    UIButton
    0.35
    kehr
    0.35
    Artificial
    0.35
    Agency
    0.34
    WEST
    0.34
    Saharan
    0.34
    Buch
    0.34
    mouseDown
    0.34
    POSITIVE LOGITS
    }",
    0.53
    }"
    0.51
    }\
    0.47
     ":
    0.46
    }'
    0.45
    }".
    0.44
     "("
    0.43
    })"
    0.43
     ",
    0.42
    ":
    0.40
    Act Density 0.041%

    No Known Activations