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

    Neuronpedia

    INDEX
    Explanations

    python class self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াঙ্গ
    0.64
    Arguments
    0.61
    Device
    0.58
     Commentary
    0.57
     సాధ
    0.56
    ोटा
    0.55
    chrotron
    0.55
    DeviceInfo
    0.55
    abus
    0.55
    ショー
    0.55
    POSITIVE LOGITS
     itemName
    0.74
    নতুন
    0.74
     पागल
    0.74
     รัก
    0.74
     ሕ
    0.73
     சுக
    0.72
    तह
    0.72
     ‪
    0.72
    კ
    0.72
     inicial
    0.71
    Act Density 0.002%

    No Known Activations