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

    Neuronpedia

    INDEX
    Explanations

    eliminating incorrect options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     politič
    0.53
    𝔯
    0.49
     паліты
    0.48
    राजनी
    0.47
    า
    0.47
    Ꭲ
    0.47
    Governance
    0.46
    tLogRow
    0.46
    躋
    0.46
    🦸
    0.46
    POSITIVE LOGITS
     Aliexpress
    0.43
     unbear
    0.39
     szüks
    0.38
     fluctu
    0.38
     frantically
    0.37
     ME
    0.37
     impeller
    0.37
    లిన
    0.36
     Ziel
    0.35
    ුවේ
    0.35
    Act Density 0.004%

    No Known Activations