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

    Neuronpedia

    INDEX
    Explanations

    long

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiplayer
    -0.07
     curb
    -0.07
     '^
    -0.07
    leanup
    -0.07
    Receive
    -0.07
    ニ
    -0.06
     Computing
    -0.06
    аток
    -0.06
    ical
    -0.06
    VICE
    -0.06
    POSITIVE LOGITS
     long
    0.08
     libertine
    0.07
     LONG
    0.07
     FactoryGirl
    0.07
     noen
    0.07
     dug
    0.06
    .mock
    0.06
     Long
    0.06
    �
    0.06
     donn
    0.06
    Act Density 0.017%

    No Known Activations