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

    Neuronpedia

    INDEX
    Explanations

    European/Scandinavian places/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hello
    -0.07
    *↵↵
    -0.06
    258
    -0.06
    Entry
    -0.06
     Tu
    -0.06
     Dum
    -0.06
     før
    -0.06
    	This
    -0.06
    :')↵
    -0.06
     unacceptable
    -0.06
    POSITIVE LOGITS
    Utility
    0.07
    distinct
    0.07
    ักส
    0.07
     Vik
    0.07
    _SHARED
    0.07
     StringUtils
    0.06
     EventBus
    0.06
    leine
    0.06
    іч
    0.06
    illon
    0.06
    Act Density 0.004%

    No Known Activations