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

    Neuronpedia

    INDEX
    Explanations

    Login

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    1
    -0.07
    С
    -0.07
    Beyond
    -0.07
    كو
    -0.07
    AKER
    -0.07
    _NOP
    -0.07
    0
    -0.07
    078
    -0.07
    Shared
    -0.07
    13
    -0.07
    POSITIVE LOGITS
     autoload
    0.07
    〕
    0.06
     Kamp
    0.06
     réfé
    0.06
    $body
    0.06
     resurrect
    0.06
     куда
    0.06
    ">{{$
    0.06
    ัมพ
    0.06
    ('?
    0.06
    Act Density 0.337%

    No Known Activations