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

    Neuronpedia

    INDEX
    Explanations

    rabies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    形成
    -0.07
    .Executor
    -0.07
    hash
    -0.07
     Feature
    -0.07
     Thermal
    -0.07
    Counter
    -0.07
    	Buffer
    -0.07
     Short
    -0.06
     thermal
    -0.06
     Emerson
    -0.06
    POSITIVE LOGITS
    (\
    0.06
     DE
    0.06
    (atom
    0.06
    abbix
    0.06
    \Dependency
    0.06
     sınav
    0.06
    .ra
    0.06
     immensely
    0.06
    RE
    0.06
    !!!!
    0.06
    Act Density 0.001%

    No Known Activations