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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kel
    -0.07
    .exec
    -0.07
    ænd
    -0.06
     estrogen
    -0.06
     GPU
    -0.06
     öden
    -0.06
    ализации
    -0.06
     ArrayBuffer
    -0.06
     ulong
    -0.06
     анализ
    -0.06
    POSITIVE LOGITS
     Specifically
    0.07
    Weapon
    0.07
     unregister
    0.06
    Anyone
    0.06
     relies
    0.06
     someone
    0.06
     Virginia
    0.06
    atisfied
    0.06
     pedestal
    0.06
     Any
    0.06
    Act Density 0.016%

    No Known Activations