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

    Neuronpedia

    INDEX
    Explanations

    phase formation or online learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ลักษณะ
    0.46
     Gossip
    0.45
    Physical
    0.45
    Biological
    0.44
     ลักษณะ
    0.43
     slipper
    0.43
    Preparation
    0.43
    毉
    0.42
     ﺍﻟ
    0.42
     рід
    0.42
    POSITIVE LOGITS
    atau
    0.52
    ited
    0.50
    ik
    0.49
    ienna
    0.44
    述
    0.44
    eng
    0.44
    ier
    0.43
    await
    0.42
    iese
    0.42
    aja
    0.42
    Act Density 0.013%

    No Known Activations