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

    Neuronpedia

    INDEX
    Explanations

    commas, by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expr
    -0.07
    ťan
    -0.06
     nosso
    -0.06
    ाभ
    -0.06
    ứng
    -0.06
    llu
    -0.06
    _chain
    -0.06
    ?page
    -0.06
    τη
    -0.06
    /ref
    -0.06
    POSITIVE LOGITS
    üsseldorf
    0.07
     Lester
    0.07
     Männer
    0.06
     کنید
    0.06
    Americans
    0.06
    WL
    0.06
     第
    0.06
     ");↵
    0.06
     Mono
    0.06
     arrogance
    0.06
    Act Density 0.020%

    No Known Activations