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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ang
    -0.07
    “How
    -0.07
    xdd
    -0.07
     structs
    -0.07
    ogl
    -0.06
     glyphs
    -0.06
    '].$
    -0.06
     mammals
    -0.06
    Chars
    -0.06
    ملكة
    -0.06
    POSITIVE LOGITS
    [][]
    0.07
    ίνει
    0.07
    .onclick
    0.07
    avel
    0.07
     contrib
    0.06
     tehlik
    0.06
    앤
    0.06
    Coll
    0.06
    GraphQL
    0.06
     hecho
    0.06
    Act Density 0.001%

    No Known Activations