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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CEOs
    -0.06
    _enabled
    -0.06
     qs
    -0.06
     blatantly
    -0.06
    getAll
    -0.06
    _BYTES
    -0.06
     зн
    -0.06
    MethodImpl
    -0.06
     upbeat
    -0.06
     Benchmark
    -0.06
    POSITIVE LOGITS
    :'/
    0.07
     Ödül
    0.07
    ický
    0.07
     apologized
    0.07
    /il
    0.07
     หน
    0.07
    cream
    0.06
    lixir
    0.06
     Webb
    0.06
     Ember
    0.06
    Act Density 0.018%

    No Known Activations