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

    Neuronpedia

    INDEX
    Explanations

    prism lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ballet
    -0.07
    анный
    -0.07
    AlmostEqual
    -0.07
    也是
    -0.07
    Block
    -0.07
     Block
    -0.07
    .Block
    -0.07
    orderby
    -0.06
    joy
    -0.06
     Premi
    -0.06
    POSITIVE LOGITS
     lens
    0.07
     Lens
    0.07
     Lexer
    0.07
     genç
    0.06
     neuro
    0.06
     focal
    0.06
     thesis
    0.06
     chọn
    0.06
    setIcon
    0.06
    Lens
    0.06
    Act Density 0.008%

    No Known Activations