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

    Neuronpedia

    INDEX
    Explanations

    ide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [z
    -0.07
     технолог
    -0.06
    z
    -0.06
     ประเภท
    -0.06
    스를
    -0.06
     Sz
    -0.06
     ключ
    -0.06
    (employee
    -0.06
    ("|
    -0.05
    .Modules
    -0.05
    POSITIVE LOGITS
     daytime
    0.09
     Signed
    0.08
    ide
    0.08
     rooftop
    0.08
     lightweight
    0.07
    -time
    0.07
    μέ
    0.07
    lit
    0.07
    HOOK
    0.07
    caption
    0.07
    Act Density 0.023%

    No Known Activations