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

    Neuronpedia

    INDEX
    Explanations

    regular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bulbs
    -0.07
     Augusta
    -0.06
    _xt
    -0.06
    ΡΙ
    -0.06
    -range
    -0.06
     bold
    -0.05
    xDF
    -0.05
    itious
    -0.05
     하나
    -0.05
    Hal
    -0.05
    POSITIVE LOGITS
    	lib
    0.07
     dès
    0.07
    ANCES
    0.06
     Skipping
    0.06
     neces
    0.06
     substantially
    0.06
     чемпион
    0.06
    =\'
    0.06
    unden
    0.06
     engage
    0.06
    Act Density 0.013%

    No Known Activations