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

    Neuronpedia

    INDEX
    Explanations

    lists and bullets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alleged
    -0.09
     manifesto
    -0.08
     backyard
    -0.08
    acies
    -0.08
    Typically
    -0.08
     démar
    -0.08
    Constr
    -0.07
    ninger
    -0.07
     supposedly
    -0.07
     akibat
    -0.07
    POSITIVE LOGITS
    timestamp
    0.08
     timestamp
    0.08
    番号
    0.08
     numbered
    0.08
    േരി
    0.08
     sorted
    0.07
    ijds
    0.07
     decorated
    0.07
    씩
    0.07
     bullets
    0.07
    Act Density 0.034%

    No Known Activations