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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipes
    -0.07
     storyt
    -0.07
    ъ
    -0.07
     as
    -0.06
     viewing
    -0.06
     butt
    -0.06
     skeptical
    -0.06
     slee
    -0.06
    OMATIC
    -0.06
    sock
    -0.06
    POSITIVE LOGITS
    _display
    0.06
     Š
    0.06
    Nit
    0.06
    >V
    0.06
    Steel
    0.06
     ViewBag
    0.06
    ])),↵
    0.06
    -cart
    0.06
    \Requests
    0.06
    �
    0.05
    Act Density 0.147%

    No Known Activations