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

    Neuronpedia

    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تول
    -0.07
     Maharashtra
    -0.06
     завод
    -0.06
     capitals
    -0.06
     그는
    -0.06
    ца
    -0.06
     За
    -0.06
     příč
    -0.06
     kilomet
    -0.06
    回答
    -0.06
    POSITIVE LOGITS
     Living
    0.08
    iration
    0.07
     lửa
    0.07
     accelerated
    0.07
     relies
    0.06
     Atomic
    0.06
     SPR
    0.06
     Ink
    0.06
    Edge
    0.06
     cloned
    0.06
    Act Density 0.001%

    No Known Activations