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

    Neuronpedia

    INDEX
    Explanations

    agon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Large
    -0.08
     Parse
    -0.07
    Ã
    -0.06
     Pets
    -0.06
     Howard
    -0.06
     Embedded
    -0.06
     rapidly
    -0.06
     conspiracy
    -0.06
    cluster
    -0.06
     rus
    -0.06
    POSITIVE LOGITS
    £
    0.07
    riority
    0.07
     trochu
    0.07
    itto
    0.06
    actable
    0.06
    Dod
    0.06
    .findElement
    0.06
    billing
    0.06
    ITTLE
    0.06
    buttonShape
    0.06
    Act Density 0.002%

    No Known Activations