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

    Neuronpedia

    INDEX
    Explanations

    Docstring explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawing
    0.46
     clandestine
    0.44
    collectionView
    0.43
     auxin
    0.41
    OPH
    0.41
     tendon
    0.40
    νον
    0.40
    vVertex
    0.39
    arken
    0.39
    AYS
    0.39
    POSITIVE LOGITS
     Verbesser
    0.52
     വൃ
    0.51
     کامل
    0.50
     Moż
    0.46
     hoàn
    0.46
    می
    0.46
     функції
    0.46
     واضح
    0.45
    მო
    0.44
     كامل
    0.44
    Act Density 0.032%

    No Known Activations