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
     cancer
    -0.82
     Cancer
    -0.79
    Cancer
    -0.71
     CANCER
    -0.67
    cancer
    -0.66
     дописавши
    -0.65
     kanker
    -0.61
     consultato
    -0.61
    Playground
    -0.60
    OGND
    -0.59
    POSITIVE LOGITS
    WebMethod
    0.55
     صوتيه
    0.52
    rrggbb
    0.49
     prieten
    0.48
     móvel
    0.47
     vermelha
    0.47
     rangs
    0.46
     marinho
    0.46
     uș
    0.45
    TabStop
    0.44
    Act Density 0.200%

    No Known Activations