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

    Neuronpedia

    INDEX
    Explanations

    personal reflection/values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <th
    -0.07
    _statement
    -0.07
    linkedin
    -0.06
     Usage
    -0.06
    Linear
    -0.06
     linear
    -0.06
    $r
    -0.06
     tur
    -0.06
     problemas
    -0.06
    Third
    -0.06
    POSITIVE LOGITS
    (userid
    0.06
    .#
    0.06
     كنت
    0.06
    χει
    0.06
     (↵
    0.06
    ierge
    0.06
    ~-
    0.06
     Hydra
    0.06
     ngay
    0.06
    (Keys
    0.06
    Act Density 0.106%

    No Known Activations