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

    Neuronpedia

    INDEX
    Explanations

    rat or mouse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Buffer
    -0.07
     Oxygen
    -0.07
     adapter
    -0.07
    lene
    -0.07
    כנע
    -0.07
     Trusted
    -0.07
    	obj
    -0.06
     tam
    -0.06
    -cont
    -0.06
    ::<
    -0.06
    POSITIVE LOGITS
    Spot
    0.07
    ismet
    0.07
    izzard
    0.07
     Shop
    0.07
    红枣
    0.07
    私服
    0.06
    强国
    0.06
    日常
    0.06
    キング
    0.06
    上下游
    0.06
    Act Density 0.023%

    No Known Activations