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

    Neuronpedia

    INDEX
    Explanations

    software developer/user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    셨
    -0.07
    lfw
    -0.07
     gras
    -0.07
    	It
    -0.06
    Interpreter
    -0.06
    _reader
    -0.06
    igua
    -0.06
    iT
    -0.06
    uras
    -0.06
    Chess
    -0.06
    POSITIVE LOGITS
     Attribute
    0.07
    /environment
    0.07
    .target
    0.07
    	form
    0.07
     Duplicate
    0.06
     -↵↵
    0.06
     kontrol
    0.06
     shortcut
    0.06
    べ
    0.06
    .schedule
    0.06
    Act Density 0.000%

    No Known Activations