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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    skými
    -0.06
    sampling
    -0.06
    relationship
    -0.06
     substitutes
    -0.06
     relationships
    -0.06
    الد
    -0.06
    .FileReader
    -0.05
    瑞
    -0.05
    information
    -0.05
    Ny
    -0.05
    POSITIVE LOGITS
    ей
    0.07
     |>
    0.07
    abilece
    0.07
    ısından
    0.07
    enting
    0.07
    -Л
    0.06
     Lent
    0.06
    -val
    0.06
    dens
    0.06
    ,but
    0.06
    Act Density 0.015%

    No Known Activations