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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sequence
    -0.07
    ská
    -0.06
     스포츠
    -0.06
    ụp
    -0.06
     şun
    -0.06
    _reader
    -0.06
     kuş
    -0.06
    /team
    -0.06
    WRAPPER
    -0.06
    あった
    -0.06
    POSITIVE LOGITS
    dif
    0.07
    .IsActive
    0.07
     intermediate
    0.07
    Sdk
    0.06
    allenges
    0.06
     Sending
    0.06
     SCH
    0.06
     economically
    0.06
    <Scalars
    0.06
    msg
    0.06
    Act Density 0.064%

    No Known Activations