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
     bunker
    -0.07
    _MULT
    -0.07
     Addition
    -0.06
    층
    -0.06
    reation
    -0.06
     butter
    -0.06
    334
    -0.06
     Township
    -0.06
     zombie
    -0.06
     Spin
    -0.06
    POSITIVE LOGITS
    _code
    0.07
    (code
    0.07
    green
    0.06
    logradouro
    0.06
    reg
    0.06
    	Debug
    0.06
    connector
    0.06
    uropean
    0.06
     opc
    0.06
    Decode
    0.06
    Act Density 0.008%

    No Known Activations