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

    Neuronpedia

    INDEX
    Explanations

    type hints and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⎦
    1.00
    %"},
    0.90
     \]
    0.86
    cemment
    0.86
    $('#
    0.86
    flatiron
    0.85
    $('
    0.84
    uestas
    0.84
     alas
    0.84
    ached
    0.83
    POSITIVE LOGITS
    و
    1.02
    ταν
    0.96
    രുവനന്തപു
    0.90
    وتا
    0.88
    ρχ
    0.87
     ontology
    0.87
    া
    0.87
    ма
    0.87
    ことになる
    0.87
    ই
    0.86
    Act Density 0.003%

    No Known Activations