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

    Neuronpedia

    INDEX
    Explanations

    opinions and discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     don
    -0.07
     wield
    -0.07
    ]>=
    -0.07
    ichtig
    -0.06
     circus
    -0.06
     Ukraj
    -0.06
    ラー
    -0.06
    <State
    -0.06
    WARD
    -0.06
     escre
    -0.06
    POSITIVE LOGITS
     INTERN
    0.07
    CLK
    0.06
     rte
    0.06
     resale
    0.06
     ┃
    0.06
    _WRITE
    0.06
    ereum
    0.06
     Norway
    0.06
     RM
    0.06
    pciones
    0.06
    Act Density 0.002%

    No Known Activations