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

    Neuronpedia

    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intelligence
    -0.08
     paddingHorizontal
    -0.06
     Lazy
    -0.06
    청
    -0.06
     Mustang
    -0.06
    )NULL
    -0.06
     جمهور
    -0.06
    興
    -0.06
    -round
    -0.06
     Sector
    -0.06
    POSITIVE LOGITS
    един
    0.06
    �
    0.06
    Slow
    0.06
    487
    0.06
     dut
    0.06
    нод
    0.06
    ode
    0.06
    ertools
    0.06
    ("%
    0.06
    dın
    0.06
    Act Density 0.007%

    No Known Activations