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

    Neuronpedia

    INDEX
    Explanations

    cancer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JACK
    -0.08
     chan
    -0.07
     status
    -0.07
     wow
    -0.07
     Ground
    -0.07
     worse
    -0.07
     worlds
    -0.06
    ारक
    -0.06
     faker
    -0.06
     ed
    -0.06
    POSITIVE LOGITS
    .share
    0.07
    लत
    0.06
     continu
    0.06
     کاهش
    0.06
    service
    0.06
     rowNum
    0.06
     brigade
    0.06
     К
    0.06
     isIn
    0.06
    aversal
    0.06
    Act Density 0.051%

    No Known Activations