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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concatenate
    -0.06
     petroleum
    -0.06
     menace
    -0.06
     stuff
    -0.06
    BG
    -0.06
     非
    -0.06
    出口
    -0.06
    wf
    -0.06
    _attributes
    -0.06
    cv
    -0.06
    POSITIVE LOGITS
     Swagger
    0.07
    ubby
    0.07
    	cout
    0.07
     obvykle
    0.07
    кому
    0.07
    SION
    0.06
    ’ex
    0.06
    RUN
    0.06
    categoria
    0.06
     ráno
    0.06
    Act Density 0.057%

    No Known Activations