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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -field
    -0.07
    Expected
    -0.07
    alker
    -0.07
    -needed
    -0.06
    Generator
    -0.06
    less
    -0.06
    filled
    -0.06
    .shared
    -0.06
    DCALL
    -0.06
    eneg
    -0.06
    POSITIVE LOGITS
    мін
    0.06
     コ
    0.06
    performance
    0.06
     بازی
    0.06
    acic
    0.06
     Atlantis
    0.06
     Researchers
    0.06
    ])){↵
    0.06
    bindung
    0.06
    ])):↵
    0.06
    Act Density 0.009%

    No Known Activations