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

    Neuronpedia

    INDEX
    Explanations

    correct/right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     half
    -0.07
    ecome
    -0.07
     algo
    -0.07
     Κου
    -0.07
     openly
    -0.07
    histoire
    -0.06
    221
    -0.06
    	load
    -0.06
     knight
    -0.06
     Wald
    -0.06
    POSITIVE LOGITS
    ейств
    0.06
     Callable
    0.06
    аб
    0.06
    �
    0.06
    сион
    0.06
    #endregion
    0.06
    icom
    0.06
     ره
    0.06
    ér
    0.06
    actor
    0.06
    Act Density 0.007%

    No Known Activations