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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eg
    -0.07
     Rum
    -0.06
    ReadWrite
    -0.06
     "".
    -0.06
    CENT
    -0.06
     believes
    -0.06
     encourages
    -0.06
     cattle
    -0.06
    PLIED
    -0.06
     мік
    -0.06
    POSITIVE LOGITS
     Dealers
    0.08
    stvo
    0.06
    reb
    0.06
    };↵↵↵↵
    0.06
     Kart
    0.06
    rait
    0.06
     klik
    0.06
    .split
    0.06
    ]:=
    0.06
     доч
    0.06
    Act Density 0.077%

    No Known Activations