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

    Neuronpedia

    INDEX
    Explanations

    measurement units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UNDER
    -0.06
    .Do
    -0.06
    iliation
    -0.06
    ListOf
    -0.06
     Bitte
    -0.06
    \Security
    -0.06
    いる
    -0.06
     Harlem
    -0.06
     "{\"
    -0.06
    (org
    -0.06
    POSITIVE LOGITS
    /items
    0.08
    zim
    0.07
    ney
    0.07
     bottles
    0.07
     encaps
    0.07
     rolls
    0.07
     roll
    0.07
     hover
    0.07
     formulas
    0.07
     cài
    0.06
    Act Density 0.003%

    No Known Activations