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

    Neuronpedia

    INDEX
    Explanations

    structuring punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szk
    0.79
    ospitals
    0.75
     alcun
    0.74
    োয়
    0.74
     தருக
    0.72
    عار
    0.72
     outsourced
    0.71
    صیٰ
    0.71
    ॉजी
    0.71
     entspricht
    0.71
    POSITIVE LOGITS
     )
    0.66
    Introdu
    0.63
    าน
    0.56
    とおり
    0.55
     impuls
    0.54
     그럼
    0.54
    阚
    0.54
    其他的
    0.53
    แสดง
    0.53
    Desen
    0.53
    Act Density 0.000%

    No Known Activations