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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     performs
    -0.06
    ۳۵
    -0.06
     pus
    -0.06
     نف
    -0.06
    ับค
    -0.06
     gyro
    -0.06
    _SEQUENCE
    -0.06
     تق
    -0.06
    .Panel
    -0.06
    бира
    -0.06
    POSITIVE LOGITS
    нівер
    0.07
    になり
    0.07
    depends
    0.06
    $out
    0.06
    Feedback
    0.06
    _Msp
    0.06
    Tags
    0.06
    (Op
    0.06
    !↵
    0.06
    <TreeNode
    0.06
    Act Density 0.023%

    No Known Activations