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

    Neuronpedia

    INDEX
    Explanations

    -time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fullfile
    -0.07
    ※
    -0.07
     rar
    -0.07
    ఆ
    -0.07
     Nationwide
    -0.07
     средне
    -0.07
    eden
    -0.06
     adjoining
    -0.06
    หลายๆ
    -0.06
     Schwar
    -0.06
    POSITIVE LOGITS
     miner
    0.07
    _PLAY
    0.07
    ”)
    0.07
    ("-",
    0.07
    (saved
    0.07
    ”,
    0.07
    port
    0.07
     liv
    0.07
    OUND
    0.07
    און
    0.07
    Act Density 0.002%

    No Known Activations