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

    Neuronpedia

    INDEX
    Explanations

    Brevity or short summaries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timestamp
    -0.07
    Fully
    -0.06
    ูม
    -0.06
    Factor
    -0.06
    _written
    -0.06
    Crop
    -0.06
     grown
    -0.06
    _rgba
    -0.06
    错误
    -0.06
     pent
    -0.06
    POSITIVE LOGITS
     paranoia
    0.08
     prá
    0.07
     knocking
    0.07
    'nun
    0.06
     chemical
    0.06
    sent
    0.06
     полот
    0.06
     ausp
    0.06
     neigh
    0.06
    Highlights
    0.06
    Act Density 0.210%

    No Known Activations