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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mã
    -0.07
    emplo
    -0.07
     }}">
    -0.06
     overrun
    -0.06
    恋
    -0.06
    ounder
    -0.06
     Jahres
    -0.06
    ンド
    -0.06
    ?>"/>↵
    -0.06
    '}).
    -0.06
    POSITIVE LOGITS
    .kill
    0.07
    eyle
    0.06
    .binary
    0.06
    _CUDA
    0.06
     composite
    0.06
    toggle
    0.06
     mean
    0.06
    tensorflow
    0.06
    =create
    0.06
    erate
    0.06
    Act Density 0.004%

    No Known Activations