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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bnb
    -0.07
     breaches
    -0.07
    _prom
    -0.07
    .roles
    -0.07
    dataSource
    -0.07
    段
    -0.06
    ">
↵
↵
    -0.06
    	left
    -0.06
    จะเป
    -0.06
    337
    -0.06
    POSITIVE LOGITS
    darwin
    0.08
    ayi
    0.06
    .ModelSerializer
    0.06
    Berlin
    0.06
     working
    0.06
    .Qt
    0.06
     subsidi
    0.06
     Sanayi
    0.06
     Sta
    0.06
     scientific
    0.06
    Act Density 0.034%

    No Known Activations