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
     Preservation
    -0.08
    ್ಞಾನ
    -0.08
     fis
    -0.08
     proclam
    -0.08
    ಾಂ
    -0.07
    ,N
    -0.07
     fint
    -0.07
    /compiler
    -0.07
     minic
    -0.07
    ಲಾಗಿದೆ
    -0.07
    POSITIVE LOGITS
    .caption
    0.08
     kayaking
    0.08
     objection
    0.08
     بج
    0.08
    depends
    0.07
     trid
    0.07
     KS
    0.07
    .sensor
    0.07
     Киев
    0.07
     ત
    0.07
    Act Density 0.011%

    No Known Activations