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

    Neuronpedia

    INDEX
    Explanations

    Academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invites
    -0.09
    留给
    -0.08
     Invitation
    -0.07
     fot
    -0.07
    atem
    -0.07
     vol
    -0.07
    ♮
    -0.06
    (console
    -0.06
     embod
    -0.06
    (BitConverter
    -0.06
    POSITIVE LOGITS
    뎠
    0.07
    ᲂ
    0.07
    рем
    0.07
    杨
    0.07
     directories
    0.07
    methodPointerType
    0.07
    ضة
    0.06
    rigesimal
    0.06
    .routing
    0.06
     Rey
    0.06
    Act Density 0.004%

    No Known Activations