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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Muss
    -0.07
    ným
    -0.06
    Merchant
    -0.06
    ντ
    -0.06
    로는
    -0.06
    Recipient
    -0.06
    ưu
    -0.06
    >Password
    -0.06
    .Pop
    -0.06
    ="_
    -0.06
    POSITIVE LOGITS
     검
    0.08
    松
    0.07
     pás
    0.07
     Buffered
    0.07
    leta
    0.06
     HttpResponseRedirect
    0.06
    Ed
    0.06
     provision
    0.06
    영
    0.06
     دوره
    0.06
    Act Density 0.000%

    No Known Activations