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
    /Add
    -0.07
    änd
    -0.06
     może
    -0.06
    "testing
    -0.06
    корист
    -0.06
    898
    -0.06
    itet
    -0.06
    jab
    -0.06
     Gauge
    -0.06
     bazı
    -0.06
    POSITIVE LOGITS
     sandwich
    0.07
    Flexible
    0.07
    旁
    0.07
     exercising
    0.06
     verbally
    0.06
     ^{}
    0.06
     elapsedTime
    0.06
     Omni
    0.06
     ankles
    0.06
    TOTAL
    0.06
    Act Density 0.004%

    No Known Activations