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

    Neuronpedia

    INDEX
    Explanations

    references to triangular shapes or structures

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

    triangular lattice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.55
     Efq
    -0.53
     juſ
    -0.53
    /**
    -0.50
     fubject
    -0.49
     themſelves
    -0.48
     ſta
    -0.46
     leſs
    -0.46
     pleaſure
    -0.45
     ainfi
    -0.44
    POSITIVE LOGITS
     triangle
    1.48
     triangular
    1.48
     Triangle
    1.43
    Triangle
    1.34
     triangles
    1.19
    triangle
    1.16
    三角
    1.12
     三角
    1.09
    Triangles
    1.04
     triang
    0.93
    Act Density 0.044%

    No Known Activations