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

    Neuronpedia

    INDEX
    Explanations

    Lasers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gments
    -0.07
     memories
    -0.07
     Edwin
    -0.06
    bab
    -0.06
    Virginia
    -0.06
    洞
    -0.06
     perl
    -0.06
    bling
    -0.06
     rifle
    -0.06
     ymax
    -0.06
    POSITIVE LOGITS
     olmayan
    0.07
    ----</
    0.06
     přibliž
    0.06
     adipisicing
    0.06
    （笑
    0.06
     góp
    0.06
    _DECL
    0.06
     переда
    0.06
     nejd
    0.06
    　　　
    0.06
    Act Density 0.013%

    No Known Activations