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

    Neuronpedia

    INDEX
    Explanations

    "this is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apprehension
    0.77
    မဟုတ်
    0.75
     त्याचे
    0.71
     управления
    0.69
     revisiting
    0.67
    kennung
    0.67
     Critic
    0.67
    eren
    0.67
    педії
    0.66
     tekr
    0.66
    POSITIVE LOGITS
    в
    0.81
    )];
    0.67
    %);
    0.66
    en
    0.65
    ti
    0.62
    )],
    0.61
    oxo
    0.59
    at
    0.59
    ि
    0.59
    िओ
    0.58
    Act Density 0.206%

    No Known Activations