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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oste
    -0.07
     dull
    -0.07
    hydration
    -0.06
     populated
    -0.06
    �
    -0.06
    reasonable
    -0.06
    яття
    -0.06
    .ud
    -0.06
    有人
    -0.06
     creepy
    -0.06
    POSITIVE LOGITS
    ,proto
    0.07
    .');↵
    0.07
    .getChild
    0.07
     Mueller
    0.06
    _box
    0.06
     ))↵
    0.06
    、日本
    0.06
     RADIO
    0.06
     QUEUE
    0.06
     Mich
    0.06
    Act Density 0.000%

    No Known Activations