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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.49
     biography
    0.48
     unanim
    0.46
     succession
    0.45
     lunchtime
    0.44
     考え
    0.43
     ambitious
    0.42
     newsletter
    0.42
     লেখকের
    0.42
     ক্ষম
    0.42
    POSITIVE LOGITS
    एक
    0.52
    As
    0.51
    å
    0.50
    Act
    0.50
    لا
    0.49
    ة
    0.48
    Ná
    0.47
    Det
    0.47
    ρα
    0.47
    butanol
    0.47
    Act Density 0.307%

    No Known Activations