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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Simone
    -0.07
    市
    -0.06
     темп
    -0.06
    	nil
    -0.06
    н
    -0.06
    enerate
    -0.06
     Zend
    -0.06
    stagram
    -0.06
    	person
    -0.06
     Born
    -0.06
    POSITIVE LOGITS
    ┐
    0.07
    >e
    0.07
    ritable
    0.06
    esso
    0.06
     Korean
    0.06
     veto
    0.06
     keyed
    0.06
     yap
    0.06
     ----------------------------------------------------------------
    0.06
    oggled
    0.06
    Act Density 0.002%

    No Known Activations