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

    Neuronpedia

    INDEX
    Explanations

    Is/are/was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Washing
    -0.07
    린
    -0.07
     cheque
    -0.07
    reserve
    -0.07
    liquid
    -0.06
     straightforward
    -0.06
     unwind
    -0.06
    AXB
    -0.06
    GINE
    -0.06
     greens
    -0.06
    POSITIVE LOGITS
    VK
    0.07
    чних
    0.07
     ustanov
    0.07
    clo
    0.06
    ~↵↵
    0.06
    �
    0.06
     rahatsız
    0.06
    ]=
    0.06
     objetivo
    0.06
     irc
    0.06
    Act Density 0.154%

    No Known Activations