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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _aut
    -0.07
     wildcard
    -0.07
     kos
    -0.06
     exercised
    -0.06
    �
    -0.06
    ±ط
    -0.06
     культу
    -0.06
     MAK
    -0.06
    -d
    -0.06
    ":"
    -0.06
    POSITIVE LOGITS
    izzling
    0.07
    lenen
    0.07
     impressed
    0.07
    forcements
    0.06
    itesse
    0.06
    орм
    0.06
     Belg
    0.06
    (blob
    0.06
     pcm
    0.06
     предпоч
    0.06
    Act Density 0.001%

    No Known Activations