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

    Neuronpedia

    INDEX
    Explanations

    repeats, times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .createQuery
    -0.07
     cougar
    -0.06
     Hurricanes
    -0.06
     devs
    -0.06
     вий
    -0.06
     predicate
    -0.06
     oppressive
    -0.06
    öt
    -0.06
     game
    -0.05
    constitutional
    -0.05
    POSITIVE LOGITS
     olduğu
    0.07
    睛
    0.07
     ΑΓ
    0.07
     yolu
    0.07
    >"+↵
    0.06
    hua
    0.06
     красив
    0.06
     Landing
    0.06
    .Atoi
    0.06
     술
    0.06
    Act Density 0.030%

    No Known Activations