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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	report
    -0.07
     panor
    -0.07
     ист
    -0.07
     collapsed
    -0.07
     Inject
    -0.06
     '\''
    -0.06
     Platz
    -0.06
    tweet
    -0.06
     cracked
    -0.06
     coded
    -0.06
    POSITIVE LOGITS
    ảy
    0.07
     �
    0.06
     JFactory
    0.06
    <T
    0.06
     Screens
    0.06
    ักษ
    0.06
     SATA
    0.06
     Ön
    0.06
    =N
    0.06
    221
    0.06
    Act Density 0.096%

    No Known Activations