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

    Neuronpedia

    INDEX
    Explanations

    sanitizer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    层
    -0.08
     layer
    -0.08
     sailing
    -0.07
    Pres
    -0.07
     lobster
    -0.07
    /en
    -0.07
     સ્ત
    -0.07
     tiers
    -0.07
     Pres
    -0.07
     प्यार
    -0.07
    POSITIVE LOGITS
     antise
    0.08
    amini
    0.08
     *@
    0.08
    .bootstrap
    0.08
    abr
    0.08
     antibacterial
    0.07
    andatu
    0.07
     Mop
    0.07
    repository
    0.07
     регулярно
    0.07
    Act Density 0.002%

    No Known Activations