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

    Neuronpedia

    INDEX
    Explanations

    elevated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thinks
    -0.07
    Marks
    -0.07
    Black
    -0.07
     strange
    -0.06
    ]=='
    -0.06
    (work
    -0.06
     workaround
    -0.06
     think
    -0.06
     productService
    -0.06
    .cons
    -0.06
    POSITIVE LOGITS
     Elevated
    0.12
     elevated
    0.12
     elev
    0.10
     elevate
    0.10
     Elev
    0.10
     elevation
    0.09
     elevator
    0.08
    EV
    0.08
    ев
    0.08
     �
    0.08
    Act Density 0.007%

    No Known Activations