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

    Neuronpedia

    INDEX
    Explanations

    WARRANTIES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /change
    -0.07
    chedulers
    -0.07
    損
    -0.06
     Convenience
    -0.06
    的话
    -0.06
    耗
    -0.06
    気
    -0.06
     uten
    -0.06
    fuck
    -0.06
     місце
    -0.06
    POSITIVE LOGITS
     Worce
    0.07
    .imp
    0.07
    perf
    0.07
     название
    0.06
     nigeria
    0.06
     IST
    0.06
    W
    0.06
     decades
    0.06
     ambiguous
    0.06
    ?-
    0.06
    Act Density 0.001%

    No Known Activations