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

    Neuronpedia

    INDEX
    Explanations

    error reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     വെ
    0.65
     Sociales
    0.64
    నాల
    0.64
     Luch
    0.63
     Provisions
    0.61
    Reveal
    0.61
     منت
    0.61
    ğun
    0.61
    คล
    0.60
    నాలను
    0.60
    POSITIVE LOGITS
     error
    4.73
     Error
    4.40
    error
    4.39
    Error
    4.33
     errors
    4.10
    エラー
    3.82
     Errors
    3.80
     ERROR
    3.74
    错误
    3.65
    errors
    3.57
    Act Density 0.552%

    No Known Activations