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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vuông
    -0.08
    еп
    -0.07
     abi
    -0.07
     Bulgarian
    -0.07
     Truth
    -0.07
     득
    -0.06
     Either
    -0.06
     marginBottom
    -0.06
     pw
    -0.06
     Somehow
    -0.06
    POSITIVE LOGITS
    ."]↵
    0.07
     mulher
    0.07
    	include
    0.06
    sono
    0.06
    Average
    0.06
     tưởng
    0.06
    ेबस
    0.06
     इसम
    0.06
    izzato
    0.06
    ertura
    0.06
    Act Density 0.005%

    No Known Activations