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
     wearer
    -0.07
     observes
    -0.07
     Geschichte
    -0.06
     industries
    -0.06
    annels
    -0.06
    serve
    -0.06
    LF
    -0.06
    لب
    -0.06
     allies
    -0.06
     Industries
    -0.06
    POSITIVE LOGITS
     '=',
    0.07
    _mA
    0.07
    Za
    0.06
     лиш
    0.06
     graffiti
    0.06
     aos
    0.06
    戲
    0.06
    ':{'
    0.06
     náv
    0.06
    enaire
    0.06
    Act Density 0.031%

    No Known Activations