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

    Neuronpedia

    INDEX
    Explanations

    girl in stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    льные
    0.49
    (),
    0.47
    τες
    0.47
    equation
    0.45
     selaku
    0.43
    ası
    0.42
     основном
    0.42
    وضوع
    0.41
    các
    0.41
    ные
    0.40
    POSITIVE LOGITS
    和一个
    0.54
     strangled
    0.46
     learns
    0.44
     designer
    0.44
     afraid
    0.44
     grumpy
    0.44
     Darth
    0.44
     despot
    0.43
     fiery
    0.42
     king
    0.42
    Act Density 0.177%

    No Known Activations