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

    Neuronpedia

    INDEX
    Explanations

    Geometry/triangles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    астер
    -0.07
    imm
    -0.07
     вывести
    -0.07
     assistant
    -0.07
    اری
    -0.07
    ack
    -0.07
     persoonlijk
    -0.07
     #
    -0.07
    িম
    -0.07
     পরীক্ষা
    -0.07
    POSITIVE LOGITS
    土地
    0.09
    …….
    0.09
     اللَّه
    0.08
     Bade
    0.08
    ceral
    0.08
     kidnapping
    0.08
     भिड
    0.08
    daughter
    0.08
     Legs
    0.08
     slicing
    0.08
    Act Density 0.054%

    No Known Activations