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

    Neuronpedia

    INDEX
    Explanations

    checking HTTP status codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ++/
    0.42
     シンプル
    0.41
    盻
    0.40
     Tuttle
    0.39
     tepi
    0.39
     EFI
    0.38
     خفیہ
    0.38
    屜
    0.38
     UIStoryboard
    0.38
    顴
    0.38
    POSITIVE LOGITS
    Thank
    0.52
    Question
    0.49
    Madam
    0.49
    Ms
    0.47
    My
    0.46
    Column
    0.46
    Member
    0.46
    Members
    0.45
     Question
    0.44
    Order
    0.44
    Act Density 0.000%

    No Known Activations