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

    Neuronpedia

    INDEX
    Explanations

    measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     욕
    -0.06
    ecera
    -0.06
     }(
    -0.06
    amak
    -0.06
    γκ
    -0.06
    Thumbnail
    -0.06
     Skywalker
    -0.06
    лом
    -0.06
    stories
    -0.05
    }),↵
    -0.05
    POSITIVE LOGITS
    _ge
    0.07
     innocence
    0.07
    _Em
    0.07
     Республи
    0.07
    м
    0.07
     pass
    0.07
    .......
    0.06
     vbox
    0.06
    -peer
    0.06
    -description
    0.06
    Act Density 0.005%

    No Known Activations