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

    Neuronpedia

    INDEX
    Explanations

    code related data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中文字幕
    -0.07
     THC
    -0.06
    [J
    -0.06
    uggling
    -0.06
    ật
    -0.06
    <LM
    -0.06
    _r
    -0.06
    ост
    -0.06
     lithium
    -0.06
     خوان
    -0.06
    POSITIVE LOGITS
    183
    0.06
     перед
    0.06
     create
    0.06
     Poison
    0.06
    lok
    0.06
     RE
    0.06
     Mon
    0.06
    stands
    0.06
    ..."↵
    0.06
    >')↵
    0.06
    Act Density 0.031%

    No Known Activations