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

    Neuronpedia

    INDEX
    Explanations

    graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     никогда
    -0.08
     спортсмен
    -0.08
    Iy
    -0.08
     speakers
    -0.08
     Speicherung
    -0.08
     etern
    -0.07
    ainer
    -0.07
    при
    -0.07
    	spec
    -0.07
     ном
    -0.07
    POSITIVE LOGITS
     triangles
    0.14
     Triangle
    0.12
     triangle
    0.12
    Triangles
    0.11
    Triangle
    0.11
    _triangle
    0.11
    triangle
    0.11
    _tri
    0.10
     triples
    0.10
     三
    0.10
    Act Density 0.022%

    No Known Activations