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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ClassLoader
    -0.06
    .ToTable
    -0.06
     멀
    -0.06
     quirky
    -0.06
     EH
    -0.06
    	cm
    -0.06
     ARP
    -0.06
     Oyun
    -0.06
    alleng
    -0.06
    agle
    -0.06
    POSITIVE LOGITS
     zahrn
    0.07
     месяца
    0.07
     gag
    0.07
     Wine
    0.07
    NotBlank
    0.06
    ظه
    0.06
     GWei
    0.06
    ць
    0.06
    زية
    0.06
    algo
    0.06
    Act Density 0.342%

    No Known Activations