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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    αν
    -0.07
    -To
    -0.07
    50
    -0.06
    _bloc
    -0.06
    ylinder
    -0.06
    L
    -0.06
    ac
    -0.06
    -to
    -0.06
     bun
    -0.06
    ,color
    -0.06
    POSITIVE LOGITS
     knull
    0.07
    一卷
    0.06
    ">'↵
    0.06
     AGE
    0.06
    ?>↵↵↵
    0.06
     [
    0.06
     kuş
    0.06
     quelque
    0.06
    {}↵↵
    0.06
    ै.
    0.06
    Act Density 0.053%

    No Known Activations