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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amine
    -0.07
     Chem
    -0.07
     То
    -0.07
    φη
    -0.06
    ully
    -0.06
    Regression
    -0.06
    -expression
    -0.06
    �
    -0.06
    	z
    -0.06
     kå
    -0.06
    POSITIVE LOGITS
    /rest
    0.08
    abis
    0.07
     upscale
    0.07
    novation
    0.07
    .setState
    0.07
    พยาบาล
    0.07
     urinary
    0.06
     파일첨부
    0.06
    ！↵
    0.06
     RootState
    0.06
    Act Density 0.115%

    No Known Activations