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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '"
    -0.06
     شاید
    -0.06
     Все
    -0.06
     narrower
    -0.06
    .dp
    -0.06
     ihrem
    -0.06
    ‚
    -0.06
    нее
    -0.06
     Sydney
    -0.06
    	UInt
    -0.06
    POSITIVE LOGITS
    _REGION
    0.06
    μένος
    0.06
     theor
    0.06
     Converter
    0.06
    ising
    0.06
     Chair
    0.06
     PROGRAM
    0.06
     disguise
    0.06
     disparate
    0.06
    .’
    0.06
    Act Density 0.008%

    No Known Activations