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

    Neuronpedia

    INDEX
    Explanations

    chemistry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estr
    -0.08
    Army
    -0.07
     Army
    -0.07
     Eagle
    -0.07
    坛
    -0.07
    ociety
    -0.07
    ﻴ
    -0.07
    �
    -0.06
     tvor
    -0.06
    -earth
    -0.06
    POSITIVE LOGITS
    sampling
    0.07
     Absolute
    0.06
    oulouse
    0.06
    subtitle
    0.06
     cheating
    0.06
    _collection
    0.06
     تاریخ
    0.06
    越
    0.06
    <String
    0.06
    .TRA
    0.06
    Act Density 0.000%

    No Known Activations