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

    Neuronpedia

    INDEX
    Explanations

    complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wpi
    0.45
    িশীল
    0.45
    десь
    0.44
    excited
    0.44
    jač
    0.44
    if
    0.44
    లే
    0.44
    세대
    0.44
    maxY
    0.43
    ありました
    0.43
    POSITIVE LOGITS
    はもちろん
    0.45
     achieves
    0.44
     приобрета
    0.44
     which
    0.43
     mounts
    0.42
     audits
    0.41
     irrevocable
    0.41
     achieving
    0.41
     covenants
    0.41
    ور
    0.41
    Act Density 0.005%

    No Known Activations