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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dden
    -0.07
     나는
    -0.07
     teenager
    -0.07
    /login
    -0.07
    <const
    -0.07
     :-↵
    -0.06
    (TypeError
    -0.06
    写道
    -0.06
    另一
    -0.06
     те
    -0.06
    POSITIVE LOGITS
    яв
    0.07
     unfavor
    0.07
    OBJ
    0.07
    _App
    0.07
    Processing
    0.07
     объя
    0.07
    Spell
    0.07
     предложения
    0.07
     weighed
    0.07
     Pb
    0.07
    Act Density 0.001%

    No Known Activations