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

    Neuronpedia

    INDEX
    Explanations

    question prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.61
    itization
    0.57
     decena
    0.56
    ॉक्स
    0.55
    ニメ
    0.55
    quate
    0.54
    rond
    0.52
    Allowed
    0.51
    ')[
    0.50
    竅
    0.50
    POSITIVE LOGITS
    dır
    0.59
     married
    0.59
     merhaba
    0.59
    総合
    0.57
    口味
    0.57
    だったら
    0.56
    ዛ
    0.56
     tuoi
    0.55
    కు
    0.54
    τι
    0.54
    Act Density 0.052%

    No Known Activations