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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cence
    -0.07
     і
    -0.07
    ，而
    -0.07
    Commerce
    -0.07
    	Connection
    -0.07
    .exit
    -0.06
     atroc
    -0.06
    OLLOW
    -0.06
     глав
    -0.06
     Governance
    -0.06
    POSITIVE LOGITS
    ihn
    0.06
    abis
    0.06
     negatives
    0.06
     typingsSlinky
    0.06
     &'
    0.06
     سان
    0.06
    Rp
    0.06
    Sch
    0.06
     asker
    0.06
    skb
    0.06
    Act Density 0.000%

    No Known Activations