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

    Neuronpedia

    INDEX
    Explanations

    adding headings or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.67
    h
    0.65
    the
    0.60
    2
    0.54
    an
    0.52
    ‌
    0.52
    сс
    0.51
    с
    0.51
    (-
    0.51
    و
    0.51
    POSITIVE LOGITS
     ketchup
    0.54
    ικού
    0.49
     оказался
    0.49
     obice
    0.48
     frontage
    0.48
    जानिए
    0.48
     Α
    0.47
     revêtu
    0.47
     инициа
    0.47
     chariot
    0.47
    Act Density 0.000%

    No Known Activations