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

    Neuronpedia

    INDEX
    Explanations

    segment, sketch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *&
    -1.55
    嫱
    -1.47
    encers
    -1.46
     ônibus
    -1.45
    adalah
    -1.43
     estadía
    -1.43
     Fußballspieler
    -1.41
    *?
    -1.40
     nebude
    -1.39
     helicópter
    -1.39
    POSITIVE LOGITS
    翃
    1.91
    on
    1.72
    ăzi
    1.65
    section
    1.60
    u
    1.56
    na
    1.52
    ayaquil
    1.52
    ta
    1.51
    Honestly
    1.49
    很不
    1.49
    Act Density 0.033%

    No Known Activations