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

    Neuronpedia

    INDEX
    Explanations

    slightly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themselves
    -0.07
     ","
    -0.07
     fields
    -0.07
     fold
    -0.06
     Trom
    -0.06
    four
    -0.06
     descr
    -0.06
    ա
    -0.06
     promote
    -0.06
     :",
    -0.06
    POSITIVE LOGITS
    awei
    0.07
    Ark
    0.06
    adolu
    0.06
    (SQLException
    0.06
    .AddTransient
    0.06
     welded
    0.06
     المو
    0.06
    amd
    0.06
    특
    0.06
    ,arg
    0.06
    Act Density 0.015%

    No Known Activations