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

    Neuronpedia

    INDEX
    Explanations

    Cause and effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Second
    -0.08
     Second
    -0.07
    -Pro
    -0.06
     rights
    -0.06
     admon
    -0.06
    50
    -0.06
     weapons
    -0.06
     anything
    -0.06
     principles
    -0.06
     envisioned
    -0.06
    POSITIVE LOGITS
    esor
    0.07
     전국
    0.06
    iphers
    0.06
    <TSource
    0.06
     ovšem
    0.06
    .TextChanged
    0.06
    rb
    0.06
     oval
    0.06
    .Validate
    0.06
    LOUD
    0.06
    Act Density 0.057%

    No Known Activations