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

    Neuronpedia

    INDEX
    Explanations

    printable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SECONDS
    -0.09
    OVERY
    -0.09
    Ukraine
    -0.09
     oversized
    -0.08
     Ukraina
    -0.08
    文件
    -0.08
    Noticias
    -0.08
    大型
    -0.08
    Italy
    -0.08
     &[
    -0.08
    POSITIVE LOGITS
    ाऱ
    0.07
    ствен
    0.07
    posable
    0.07
    ੈ
    0.07
     vibr
    0.07
     резко
    0.07
    inecraft
    0.07
     vamp
    0.07
     тщательно
    0.07
     предус
    0.07
    Act Density 0.000%

    No Known Activations