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

    Neuronpedia

    INDEX
    Explanations

    geometric terms and shapes associated with physical structures or components

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

    Geometric shapes

    np_acts-logits-general · gemini-2.0-flash

    geometric shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    },[])
    -0.53
     vicenda
    -0.53
    agaimana
    -0.49
     объя
    -0.49
    Демо
    -0.49
     CreateTagHelper
    -0.48
     Италијани
    -0.48
     titolo
    -0.47
     paſſ
    -0.47
    qtype
    -0.47
    POSITIVE LOGITS
     rectangular
    1.17
     flat
    1.16
     triangular
    1.10
     round
    1.09
     oval
    1.08
     rounded
    1.07
     square
    1.05
     oblong
    1.03
     rectangle
    1.01
     triangle
    0.99
    Act Density 0.522%

    No Known Activations