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

    Neuronpedia

    INDEX
    Explanations

    wood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ित
    -0.07
     rings
    -0.07
    Wild
    -0.07
    $model
    -0.07
     Wild
    -0.07
    allowed
    -0.07
    Ru
    -0.07
     卡
    -0.06
     Shut
    -0.06
    発
    -0.06
    POSITIVE LOGITS
     layui
    0.06
    .ZERO
    0.06
    \F
    0.06
     Connect
    0.06
     interviews
    0.06
    mise
    0.06
    .TabPage
    0.06
    _PH
    0.06
    PCODE
    0.06
    laması
    0.06
    Act Density 0.024%

    No Known Activations