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

    Neuronpedia

    INDEX
    Explanations

    code/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Containing
    -0.07
    スの
    -0.07
     hjem
    -0.06
     ساده
    -0.06
    市場
    -0.06
     woodland
    -0.06
    .basename
    -0.06
    TCP
    -0.06
    MU
    -0.06
     creeping
    -0.06
    POSITIVE LOGITS
     eso
    0.07
    >.
    0.07
    
    0.07
     specifics
    0.07
    ,System
    0.07
     hebben
    0.06
     Nüfus
    0.06
     useEffect
    0.06
    once
    0.06
    狗
    0.06
    Act Density 0.001%

    No Known Activations