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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     희
    -0.07
    -flight
    -0.07
     způsobem
    -0.07
    variants
    -0.07
    ятно
    -0.07
    .Copy
    -0.07
    ας
    -0.06
     redistrib
    -0.06
    .goBack
    -0.06
     gitti
    -0.06
    POSITIVE LOGITS
     issu
    0.06
     '\''
    0.06
    .req
    0.06
     indoor
    0.06
     Oper
    0.06
     Alexandre
    0.06
     svém
    0.06
    ','"+
    0.06
     vow
    0.06
     امیر
    0.06
    Act Density 0.005%

    No Known Activations