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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doi
    -0.07
    icrobial
    -0.07
    /english
    -0.06
    transform
    -0.06
     connects
    -0.06
     enchanted
    -0.06
     leaks
    -0.06
    Except
    -0.06
    .Select
    -0.06
     leaked
    -0.06
    POSITIVE LOGITS
    вол
    0.07
    .Navigate
    0.07
     acı
    0.07
    ฤศจ
    0.06
    ################################################
    0.06
    (日
    0.06
    Executable
    0.06
    ociety
    0.06
    ونية
    0.06
    expenses
    0.06
    Act Density 0.000%

    No Known Activations