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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Submitting
    -0.09
     European
    -0.08
     statistical
    -0.08
     rejection
    -0.07
     trials
    -0.07
    ISOString
    -0.07
     foul
    -0.07
     kabul
    -0.07
     rejects
    -0.07
     rejecting
    -0.07
    POSITIVE LOGITS
     kwartaal
    0.09
    万美元
    0.09
     anecdotes
    0.09
     مقت
    0.09
     מדר
    0.09
     campers
    0.09
    万元
    0.08
    osevelt
    0.08
     올해
    0.08
    万円
    0.08
    Act Density 0.005%

    No Known Activations