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

    Neuronpedia

    INDEX
    Explanations

    terms related to geometric shapes and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    shape, object, and physical properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.65
    GOTREF
    -0.60
     kasarigan
    -0.58
     propOrder
    -0.58
    SharedCtor
    -0.57
     desmotivaciones
    -0.56
    pushFollow
    -0.55
    jména
    -0.54
    findpost
    -0.52
    раздо
    -0.51
    POSITIVE LOGITS
    物体
    0.46
     dev
    0.43
     objects
    0.40
     geometric
    0.39
     toys
    0.38
     object
    0.38
     geometri
    0.37
     color
    0.35
    물
    0.35
     solid
    0.35
    Act Density 0.189%

    No Known Activations