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

    Neuronpedia

    INDEX
    Explanations

    potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atorship
    0.46
    AGUE
    0.46
    aday
    0.45
    sembling
    0.45
     figurine
    0.44
    ifie
    0.42
     কিছুই
    0.42
     Waldorf
    0.42
    er
    0.41
    alh
    0.41
    POSITIVE LOGITS
    し
    0.48
     ingested
    0.48
    磯
    0.48
     is
    0.47
    上
    0.46
     acetylene
    0.45
     گیا
    0.44
    ジ
    0.44
     immutable
    0.44
    平
    0.43
    Act Density 0.001%

    No Known Activations