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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .flex
    -0.07
    assistant
    -0.06
     товар
    -0.06
    ustral
    -0.06
    _IN
    -0.06
    _goods
    -0.06
    fh
    -0.06
    .getName
    -0.06
     üretim
    -0.06
     Dut
    -0.06
    POSITIVE LOGITS
     cloak
    0.07
    	opts
    0.07
     CCP
    0.06
     Alla
    0.06
     locksmith
    0.06
     istih
    0.06
    	Context
    0.06
    \Builder
    0.06
    ttp
    0.06
     EFF
    0.06
    Act Density 0.054%

    No Known Activations