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

    Neuronpedia

    INDEX
    Explanations

    rot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Awesome
    -0.07
     Cuộc
    -0.06
     원
    -0.06
     pens
    -0.06
    ],↵↵
    -0.06
    丰富
    -0.06
     require
    -0.06
    情况来看
    -0.06
    东莞市
    -0.06
     [])↵
    -0.06
    POSITIVE LOGITS
    UIFont
    0.07
     deaf
    0.07
    เคล
    0.07
    nf
    0.06
     Protest
    0.06
    弑
    0.06
     prote
    0.06
    CAPE
    0.06
    (Unit
    0.06
    boa
    0.06
    Act Density 0.004%

    No Known Activations