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

    Neuronpedia

    INDEX
    Explanations

    lack of explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ủa
    0.19
    يا
    0.19
    का
    0.17
    いる
    0.16
     a
    0.16
     THAT
    0.16
     iyong
    0.16
     危
    0.16
     zwy
    0.16
    こ
    0.16
    POSITIVE LOGITS
     Especific
    0.19
     குறிப்பிட
    0.16
    具体的な
    0.16
    MR
    0.16
     mention
    0.16
    EPC
    0.15
     учета
    0.15
    espec
    0.14
    OT
    0.14
     особенностей
    0.14
    Act Density 0.488%

    No Known Activations