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

    Neuronpedia

    INDEX
    Explanations

    inception to completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ränkt
    0.59
     تساعد
    0.54
     সহযোগ
    0.54
    ช่วย
    0.53
    য়োজনীয়
    0.52
     পদ্ধতিতে
    0.52
     gewüns
    0.52
     nöt
    0.51
     möchte
    0.51
     사용할
    0.51
    POSITIVE LOGITS
     inception
    1.84
     onset
    1.72
     commencement
    1.68
     arrival
    1.65
    开始
    1.51
    開始
    1.47
     initiation
    1.47
     início
    1.45
     inicio
    1.41
    onset
    1.41
    Act Density 0.665%

    No Known Activations