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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Blooming
    0.48
    Acknowledg
    0.46
    !।
    0.45
    Hara
    0.45
    Noeud
    0.44
    Histoire
    0.43
    приклад
    0.42
    ␶
    0.42
     робити
    0.42
     поднима
    0.41
    POSITIVE LOGITS
     [];
    0.53
    from
    0.50
     {};
    0.50
     '';
    0.48
    new
    0.48
     new
    0.47
     that
    0.46
     we
    0.46
     "";
    0.45
     from
    0.45
    Act Density 0.104%

    No Known Activations