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
     chce
    -0.07
    aje
    -0.07
     avoir
    -0.07
    ави
    -0.06
     여
    -0.06
    .AspNetCore
    -0.06
     eğ
    -0.06
    -des
    -0.06
     coral
    -0.06
    _indent
    -0.06
    POSITIVE LOGITS
    .pack
    0.07
     холодиль
    0.07
     마음
    0.06
    ＼↵
    0.06
    azeera
    0.06
     Bloomberg
    0.06
     мел
    0.06
    _finalize
    0.06
    backward
    0.06
    (bc
    0.06
    Act Density 0.000%

    No Known Activations