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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nevy
    -0.06
     mercado
    -0.06
    絵
    -0.06
     긴
    -0.06
    clide
    -0.06
     Hour
    -0.06
     Arthropoda
    -0.06
    .save
    -0.06
    Tau
    -0.06
    국의
    -0.06
    POSITIVE LOGITS
     Rach
    0.06
    ¢
    0.06
    .appspot
    0.06
     naw
    0.06
     LL
    0.06
    States
    0.06
     MO
    0.06
    ellij
    0.06
    Downloader
    0.06
     hava
    0.06
    Act Density 0.016%

    No Known Activations