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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polynomials
    0.90
    জমেন্ট
    0.86
     checkboxes
    0.82
     dropdown
    0.82
     rende
    0.80
    冚
    0.79
    ້ອຍ
    0.79
     "*************
    0.79
    ्मण
    0.78
    갑습니다
    0.77
    POSITIVE LOGITS
    态度
    1.05
     stále
    1.02
    놈
    0.91
    dealing
    0.89
    ยังมี
    0.88
    Reporting
    0.85
    Hor
    0.85
    }}(\
    0.84
    স
    0.83
     myös
    0.82
    Act Density 0.062%

    No Known Activations