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

    Neuronpedia

    INDEX
    Explanations

    compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chars
    -0.07
    SCRIPTOR
    -0.07
    balanced
    -0.07
    Exclude
    -0.07
     Whenever
    -0.06
    PIO
    -0.06
     Counsel
    -0.06
     merge
    -0.06
     free
    -0.06
    LOCATION
    -0.06
    POSITIVE LOGITS
    290
    0.07
    /Core
    0.07
    /html
    0.07
     Ste
    0.06
     :)
    0.06
    Ě
    0.06
    -metal
    0.06
    Bezier
    0.06
    λλην
    0.06
    Td
    0.06
    Act Density 0.004%

    No Known Activations