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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (src
    -0.07
    _DGRAM
    -0.07
    Hyper
    -0.07
     RESULT
    -0.07
    SUP
    -0.07
     RECORD
    -0.07
     تور
    -0.07
    _TERM
    -0.06
    σου
    -0.06
     Team
    -0.06
    POSITIVE LOGITS
    cfg
    0.07
    *.
    0.07
    нош
    0.07
    え
    0.06
    SUR
    0.06
     *.
    0.06
     코로나
    0.06
    gili
    0.06
     â
    0.06
    	   ↵
    0.06
    Act Density 0.003%

    No Known Activations