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

    Neuronpedia

    INDEX
    Explanations

    Actions and Investing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     меня
    -0.07
     wonderful
    -0.07
    xiety
    -0.07
    ‘s
    -0.06
     saga
    -0.06
     вп
    -0.06
    :A
    -0.06
    GOOD
    -0.06
    laps
    -0.06
     Gab
    -0.06
    POSITIVE LOGITS
    alarını
    0.07
    ialog
    0.06
     ERC
    0.06
     Palin
    0.06
    ρά
    0.06
    ercul
    0.06
    _scores
    0.06
     ETA
    0.06
     dispar
    0.06
     조금
    0.06
    Act Density 0.223%

    No Known Activations