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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utt
    -0.06
     tut
    -0.06
     midway
    -0.06
    “And
    -0.06
    _len
    -0.06
    ’all
    -0.06
    чес
    -0.06
     visits
    -0.06
     concaten
    -0.06
     sushi
    -0.05
    POSITIVE LOGITS
     obvious
    0.07
    不是
    0.07
    ＼
    0.06
    ็อต
    0.06
     Bliss
    0.06
    Comic
    0.06
     اختص
    0.06
    arranty
    0.06
     Osaka
    0.06
    AA
    0.06
    Act Density 0.000%

    No Known Activations