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

    Neuronpedia

    INDEX
    Explanations

    planets orbiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.66
    ad
    0.62
    Q
    0.58
    im
    0.56
    id
    0.53
    m
    0.53
    ง
    0.53
    AR
    0.52
    ar
    0.51
    W
    0.51
    POSITIVE LOGITS
     nameWithOwner
    0.57
     anabolic
    0.52
     underdog
    0.49
    స్కీ
    0.48
     Pltf
    0.46
     guava
    0.46
     stoichi
    0.46
    ১২শ
    0.45
     ağı
    0.45
     endomet
    0.45
    Act Density 0.007%

    No Known Activations