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

    Neuronpedia

    INDEX
    Explanations

    servo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stock
    -0.07
    -element
    -0.07
    tester
    -0.06
    Prop
    -0.06
    Desk
    -0.06
    _sta
    -0.06
     '\
    -0.06
     Decor
    -0.06
     Dict
    -0.06
    恢
    -0.06
    POSITIVE LOGITS
     McLaren
    0.06
     Crushing
    0.06
    ա
    0.06
    Australia
    0.06
    :"-
    0.06
    bled
    0.06
    ?");↵
    0.06
    _direct
    0.05
    ,u
    0.05
    "),
↵
    0.05
    Act Density 0.006%

    No Known Activations