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

    Neuronpedia

    INDEX
    Explanations

    lab experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    capacity
    -0.07
     servlet
    -0.07
     trạng
    -0.07
    levance
    -0.07
    pthread
    -0.06
    (pthread
    -0.06
     Query
    -0.06
     Angiospermae
    -0.06
    _THRESH
    -0.06
    Explore
    -0.06
    POSITIVE LOGITS
    aphrag
    0.06
     perpetrator
    0.06
     دار
    0.06
     συμβ
    0.06
    [...,
    0.05
     복
    0.05
    overnment
    0.05
     Tam
    0.05
    tam
    0.05
     avent
    0.05
    Act Density 0.019%

    No Known Activations