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

    Neuronpedia

    INDEX
    Explanations

    Julius

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rainbow
    -0.08
    离
    -0.07
     presidents
    -0.06
    接
    -0.06
    ність
    -0.06
    ich
    -0.06
    ücken
    -0.06
     echoed
    -0.06
    oldemort
    -0.06
     increase
    -0.06
    POSITIVE LOGITS
     Giants
    0.06
    Bloc
    0.06
    attrib
    0.06
     Gri
    0.06
     BufferedReader
    0.06
     exchanges
    0.06
     Gerard
    0.06
    moil
    0.06
    вают
    0.06
    Greg
    0.06
    Act Density 0.007%

    No Known Activations