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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unta
    -0.06
    unte
    -0.06
    						
↵
    -0.06
    ạn
    -0.06
     -->↵↵↵
    -0.06
    긔
    -0.06
     easier
    -0.06
     saldo
    -0.06
    ีข
    -0.06
     Hoàng
    -0.06
    POSITIVE LOGITS
    _global
    0.06
    _fl
    0.06
    _Pre
    0.06
    _tt
    0.06
    (rgb
    0.06
    =m
    0.06
    $l
    0.06
    <iostream
    0.06
     statt
    0.06
    iteur
    0.06
    Act Density 0.011%

    No Known Activations