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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ViewHolder
    -0.08
     triggering
    -0.07
     Injection
    -0.07
     presidents
    -0.07
     numbering
    -0.07
    )sender
    -0.07
     Schools
    -0.07
    .NULL
    -0.07
    )↵↵↵↵
    -0.06
    repeat
    -0.06
    POSITIVE LOGITS
     Knicks
    0.08
     (*((
    0.07
     kindly
    0.06
    Logical
    0.06
    inery
    0.06
     Clar
    0.06
    acers
    0.06
    .te
    0.06
    [date
    0.06
    brace
    0.06
    Act Density 0.009%

    No Known Activations