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

    Neuronpedia

    INDEX
    Explanations

    catal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Birch
    -0.08
     BEN
    -0.07
    uddle
    -0.07
    ='$
    -0.07
     Blake
    -0.07
    ис
    -0.07
     Madison
    -0.07
     Miller
    -0.07
     Jack
    -0.07
    若干
    -0.06
    POSITIVE LOGITS
    (".")
    0.08
     televised
    0.08
    categoria
    0.07
     względu
    0.07
    zeichnet
    0.07
    大涨
    0.07
     heating
    0.07
     eventData
    0.07
     tệ
    0.07
    DATED
    0.06
    Act Density 0.006%

    No Known Activations