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

    Neuronpedia

    INDEX
    Explanations

    Scientific/medical paper citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etrize
    -0.07
    ,},↵
    -0.06
     defin
    -0.06
     �
    -0.06
    єш
    -0.06
     contenders
    -0.06
    过
    -0.06
    ********************************************************************************
    -0.06
    詳細
    -0.06
     effected
    -0.05
    POSITIVE LOGITS
    animated
    0.08
    elm
    0.07
    :no
    0.07
    )(_
    0.07
    .removeChild
    0.07
    .Vertex
    0.06
    hton
    0.06
     editing
    0.06
     tay
    0.06
     snippets
    0.06
    Act Density 0.004%

    No Known Activations