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

    Neuronpedia

    INDEX
    Explanations

    clarity, cloning, clustering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bring
    0.70
    нев
    0.64
    yd
    0.64
    กำลัง
    0.61
    लेश्वर
    0.61
    yl
    0.60
    dataloader
    0.60
     ch
    0.60
     Norris
    0.59
    chenko
    0.59
    POSITIVE LOGITS
     Clone
    0.85
    Cl
    0.82
     Kl
    0.77
     clone
    0.77
    erical
    0.75
     Cl
    0.74
     cl
    0.74
    Clone
    0.73
    镍
    0.73
    incial
    0.73
    Act Density 0.031%

    No Known Activations