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

    Neuronpedia

    INDEX
    Explanations

    method overrides and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PSW
    0.46
    விலான
    0.41
    ਣਾ
    0.39
    俱乐部
    0.39
     पाण
    0.39
     relaxation
    0.38
     clubs
    0.38
    更换
    0.38
     землі
    0.38
     appuy
    0.37
    POSITIVE LOGITS
     override
    0.59
     actionPerformed
    0.55
     overridden
    0.53
     Override
    0.52
    Override
    0.52
    override
    0.52
    onRequest
    0.50
     onRequest
    0.49
     overriding
    0.46
     hashCode
    0.45
    Act Density 0.012%

    No Known Activations