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
     손
    -0.06
     sentinel
    -0.06
     ・
    -0.06
     Austr
    -0.06
    링
    -0.06
     ویر
    -0.06
     Antique
    -0.06
    saida
    -0.06
    HRESULT
    -0.06
    ,*
    -0.06
    POSITIVE LOGITS
     assumes
    0.06
    _logging
    0.06
     acknowledgement
    0.06
     pictures
    0.06
    Expand
    0.06
     nonsense
    0.06
     wrapping
    0.06
     eligible
    0.06
     libertine
    0.06
     downside
    0.06
    Act Density 0.006%

    No Known Activations