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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _curr
    -0.07
    403
    -0.07
    839
    -0.06
    ()
↵
↵
↵
    -0.06
     sharply
    -0.06
     prod
    -0.06
     width
    -0.06
     var
    -0.06
    206
    -0.06
     teachers
    -0.06
    POSITIVE LOGITS
    osu
    0.08
    (resultado
    0.07
    osl
    0.07
    adoo
    0.06
    æk
    0.06
     Ül
    0.06
    _GENERIC
    0.06
    ainted
    0.06
    рити
    0.06
    맨
    0.06
    Act Density 0.044%

    No Known Activations