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

    Neuronpedia

    INDEX
    Explanations

    introducing word problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مقابلہ
    0.48
     setback
    0.47
     سبسڈی
    0.46
     حق
    0.44
     شركات
    0.43
     coeffs
    0.43
     محم
    0.43
     ঘাট
    0.42
    Nim
    0.41
     payroll
    0.41
    POSITIVE LOGITS
    atem
    0.53
    トン
    0.53
    ᱓
    0.51
    𝚖
    0.47
    cheduled
    0.47
    一同
    0.47
    х
    0.45
    せ
    0.44
    úsc
    0.44
    ocaine
    0.44
    Act Density 0.003%

    No Known Activations