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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corridor
    -0.08
    GetMapping
    -0.08
    _cred
    -0.07
    =start
    -0.07
     Renew
    -0.07
     xpath
    -0.07
     rk
    -0.07
    相干
    -0.07
    ='-
    -0.07
    相比之下
    -0.07
    POSITIVE LOGITS
     continental
    0.07
    ansa
    0.07
    .square
    0.07
    治疗
    0.07
    诊治
    0.06
     Plate
    0.06
    ystack
    0.06
     обо
    0.06
    andel
    0.06
    ASK
    0.06
    Act Density 0.011%

    No Known Activations