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

    Neuronpedia

    INDEX
    Explanations

    Court appeals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Jasper
    -0.07
     nail
    -0.07
     безопасности
    -0.06
    ♁
    -0.06
     natur
    -0.06
    뽑
    -0.06
    typescript
    -0.06
     Johannes
    -0.06
     vídeos
    -0.06
    POSITIVE LOGITS
     Streets
    0.07
    /#
    0.07
    煊
    0.07
    preh
    0.07
    MT
    0.06
    .enterprise
    0.06
    的老
    0.06
    >(),
    0.06
     Pew
    0.06
     поверхност
    0.06
    Act Density 0.008%

    No Known Activations