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

    Neuronpedia

    INDEX
    Explanations

    volunteer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    streams
    -0.06
    Storage
    -0.06
    change
    -0.06
     trails
    -0.06
    .Types
    -0.06
    prime
    -0.06
    _small
    -0.06
     frequently
    -0.06
     Boxes
    -0.06
    -band
    -0.06
    POSITIVE LOGITS
     πέ
    0.07
    ayıp
    0.06
    ‌م
    0.06
    τα
    0.06
    .fe
    0.06
    ("***
    0.06
     bucket
    0.06
    aterno
    0.06
     emanc
    0.05
    <Response
    0.05
    Act Density 0.328%

    No Known Activations