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

    Neuronpedia

    INDEX
    Explanations

    major aid security date IF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ฉาก
    0.81
     खेल
    0.75
     burb
    0.73
    ถูก
    0.73
    ชอบ
    0.72
    stylish
    0.70
    Locked
    0.70
    libat
    0.70
     Radiat
    0.70
    막
    0.68
    POSITIVE LOGITS
    رش
    0.77
    வா
    0.75
    യാ
    0.73
     индивидуа
    0.71
     previous
    0.69
     konstruk
    0.68
    過去
    0.68
     temper
    0.67
     statements
    0.67
     ब्री
    0.67
    Act Density 0.000%

    No Known Activations