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

    Neuronpedia

    INDEX
    Explanations

    Kiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ную
    2.00
    sizes
    1.94
     Padua
    1.92
    ો
    1.92
    sb
    1.88
    sources
    1.84
    s
    1.84
     correctes
    1.83
    spe
    1.82
    sr
    1.82
    POSITIVE LOGITS
    ባድ
    2.16
     וכ
    2.11
    heten
    2.06
    在于
    2.03
     thước
    2.03
     তবে
    1.91
    ᥒ
    1.90
    ellä
    1.88
    వలం
    1.87
    。
    1.84
    Act Density 0.572%

    No Known Activations