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

    Neuronpedia

    INDEX
    Explanations

    environment variables and code indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kurzer
    0.13
     rzecz
    0.13
     gild
    0.13
    abelian
    0.12
     .........
    0.12
    𝙮
    0.12
    yuan
    0.12
    ]."
    0.12
    🧛
    0.12
    ியுள்ளது
    0.12
    POSITIVE LOGITS
    As
    0.13
    之所以
    0.13
    С
    0.13
    プロ
    0.12
    ibis
    0.12
     アル
    0.11
    ps
    0.11
     プロ
    0.11
    Pass
    0.11
     Settings
    0.11
    Act Density 3.215%

    No Known Activations