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

    Neuronpedia

    INDEX
    Explanations

    preventing defects or data structure columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ச்சி
    0.42
    getCql
    0.42
    োষ
    0.40
    欧洲
    0.40
    食べる
    0.40
     newcom
    0.38
     Woch
    0.38
     እንኳን
    0.38
     European
    0.37
     ইউরোপ
    0.37
    POSITIVE LOGITS
    TN
    0.44
    HN
    0.42
    BN
    0.42
    HD
    0.40
    Duty
    0.38
     HN
    0.38
    HV
    0.37
    UTC
    0.37
    TD
    0.37
    купки
    0.37
    Act Density 0.000%

    No Known Activations