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

    Neuronpedia

    INDEX
    Explanations

    solution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dok
    -0.07
     유지
    -0.07
    strar
    -0.07
     reserve
    -0.07
     traveller
    -0.06
     fatigue
    -0.06
     spéc
    -0.06
     storia
    -0.06
    しない
    -0.06
     vatandaş
    -0.06
    POSITIVE LOGITS
     solution
    0.10
    解决
    0.07
     solutions
    0.07
    ρωπα
    0.07
     blend
    0.06
     اجرای
    0.06
    ních
    0.06
    イド
    0.06
     Solution
    0.06
    esty
    0.06
    Act Density 0.043%

    No Known Activations