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

    Neuronpedia

    INDEX
    Explanations

    Court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eu
    -0.07
     macht
    -0.07
    뵉
    -0.07
    etically
    -0.07
    Ԏ
    -0.06
     run
    -0.06
     defining
    -0.06
     attorney
    -0.06
    🆙
    -0.06
    댘
    -0.06
    POSITIVE LOGITS
    /rest
    0.07
    _Box
    0.07
     InvalidOperationException
    0.07
    .TestTools
    0.07
    .Right
    0.07
    周刊
    0.07
    -uri
    0.07
     toilets
    0.06
    BYTES
    0.06
     dizzy
    0.06
    Act Density 0.003%

    No Known Activations