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

    Neuronpedia

    INDEX
    Explanations

    english wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JOIN
    0.68
    Join
    0.65
    Paste
    0.63
     США
    0.63
    NSLog
    0.62
    CellValue
    0.61
    FundMe
    0.60
     gluing
    0.60
     JOIN
    0.60
    }))
    0.59
    POSITIVE LOGITS
    ैक
    0.92
     در
    0.80
     दिले
    0.80
     uner
    0.78
    ślin
    0.77
     ik
    0.75
    మూ
    0.74
     ciem
    0.74
    ဢ
    0.74
    barung
    0.74
    Act Density 0.034%

    No Known Activations