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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes and their properties

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

    Triangles or triangular shapes

    np_acts-logits-general · gemini-2.0-flash

    triangles and crosses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ウター
    -0.41
    Життєпис
    -0.36
    NavController
    -0.33
    ]")]
    -0.32
    cierge
    -0.32
     moder
    -0.31
    ствии
    -0.31
     NavController
    -0.30
    bietern
    -0.30
     massa
    -0.29
    POSITIVE LOGITS
    QUADS
    0.72
     rectangle
    0.71
     Rectangle
    0.69
     shaped
    0.69
     triangle
    0.69
    shaped
    0.68
     triangular
    0.67
     HasFactory
    0.66
    rectangle
    0.64
    ValueStyle
    0.63
    Act Density 0.622%

    No Known Activations