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
    ekce
    -0.07
    Delete
    -0.06
    _broadcast
    -0.06
     dun
    -0.06
     dall
    -0.06
    DBG
    -0.06
    mse
    -0.06
    .tmp
    -0.06
     Expedition
    -0.06
    named
    -0.06
    POSITIVE LOGITS
    arial
    0.08
    (input
    0.08
    .’↵↵
    0.07
    [at
    0.07
    CAR
    0.07
     pošk
    0.07
    örü
    0.06
    ();
↵
↵
↵
    0.06
    ौट
    0.06
     ;
↵
↵
    0.06
    Act Density 0.022%

    No Known Activations