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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unmistak
    -0.07
     standards
    -0.06
    mu
    -0.06
    -degree
    -0.06
    variants
    -0.06
     Analytics
    -0.06
    -cut
    -0.06
     noises
    -0.06
    ira
    -0.06
     foto
    -0.06
    POSITIVE LOGITS
    โทร
    0.06
     предпол
    0.06
    (receiver
    0.06
     &(
    0.06
    >i
    0.06
    นวย
    0.06
     Rope
    0.06
     underrated
    0.06
     الب
    0.06
     QText
    0.06
    Act Density 0.126%

    No Known Activations