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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NIC
    -0.07
    ока
    -0.07
    質
    -0.06
    ias
    -0.06
     statusCode
    -0.06
     politique
    -0.06
     NIL
    -0.06
    nic
    -0.06
    ิน
    -0.06
     Crypt
    -0.06
    POSITIVE LOGITS
    10
    0.08
    Aug
    0.07
     reserved
    0.06
     деле
    0.06
    taken
    0.06
    AX
    0.06
     Aug
    0.06
     मतलब
    0.06
    Senator
    0.06
     Futures
    0.06
    Act Density 0.016%

    No Known Activations