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

    Neuronpedia

    INDEX
    Explanations

    unlocking potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vain
    0.41
    妣
    0.40
     أخ
    0.39
     തുടർ
    0.39
    fragment
    0.39
    യിലേക്ക്
    0.39
    Characteristic
    0.38
    过程中
    0.37
    unehm
    0.37
    范围内
    0.37
    POSITIVE LOGITS
     speeds
    0.43
     maths
    0.40
     Rn
    0.40
     Lebens
    0.40
     waxes
    0.39
     معاہد
    0.38
     cycles
    0.37
     consenting
    0.37
     skar
    0.37
     skewers
    0.37
    Act Density 0.000%

    No Known Activations