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

    Neuronpedia

    INDEX
    Explanations

    entities, danger, others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cartoonist
    0.50
    合适
    0.49
    畔
    0.47
     কীট
    0.45
     Humor
    0.45
     CART
    0.44
     सीताराम
    0.44
     curator
    0.43
     सब्जी
    0.43
     искусство
    0.43
    POSITIVE LOGITS
    い
    0.62
    et
    0.54
    на
    0.52
    जागरण
    0.52
    nesto
    0.51
    ཋ
    0.51
    It
    0.49
     suspects
    0.49
    ara
    0.49
    au
    0.49
    Act Density 0.000%

    No Known Activations