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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cedes
    -0.07
     Brom
    -0.06
     ignition
    -0.06
     stories
    -0.06
     reforms
    -0.06
    कर
    -0.06
    ्वत
    -0.06
     Xbox
    -0.06
    -ion
    -0.05
    Bold
    -0.05
    POSITIVE LOGITS
     récup
    0.07
    ्रत
    0.07
     прот
    0.07
    anges
    0.07
    ška
    0.07
     ウ
    0.06
     mús
    0.06
    اى
    0.06
     być
    0.06
     năng
    0.06
    Act Density 0.038%

    No Known Activations