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

    Neuronpedia

    INDEX
    Explanations

    _vertical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (control
    -0.07
    Þ
    -0.07
    нка
    -0.06
    ー�
    -0.06
    ğiniz
    -0.06
     stylist
    -0.06
    لو
    -0.06
    plevel
    -0.06
    ınız
    -0.06
     USE
    -0.06
    POSITIVE LOGITS
    [,
    0.06
    _DT
    0.06
     prism
    0.06
     चरण
    0.06
     [...
    0.06
    안
    0.06
    쳤다
    0.06
    _Address
    0.06
    ={['
    0.06
    �p
    0.06
    Act Density 0.001%

    No Known Activations