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

    Neuronpedia

    INDEX
    Explanations

    на

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ebi
    -0.08
     Mannheim
    -0.08
    ”
    -0.08
     besteh
    -0.08
     Philly
    -0.08
     estad
    -0.07
     infringement
    -0.07
    ipping
    -0.07
    aturing
    -0.07
    rail
    -0.07
    POSITIVE LOGITS
     enthusiasm
    0.13
     excitement
    0.11
     entusiasmo
    0.11
     enthousiasme
    0.11
     gratitude
    0.10
    激情
    0.10
    興
    0.10
     enthous
    0.09
     admiration
    0.09
     confiance
    0.09
    Act Density 0.015%

    No Known Activations