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

    Neuronpedia

    INDEX
    Explanations

    code termination semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    к
    0.52
    س
    0.43
     koleg
    0.41
    {
    0.41
    s
    0.38
     clasific
    0.38
    executor
    0.37
    Width
    0.37
     šta
    0.37
    Quando
    0.37
    POSITIVE LOGITS
    ԁ
    0.49
     weekend
    0.46
     placa
    0.46
     debacle
    0.45
     afterlife
    0.44
     harassment
    0.44
     flea
    0.44
    lf
    0.44
     rheumatism
    0.43
    䡈
    0.43
    Act Density 0.002%

    No Known Activations