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

    Neuronpedia

    INDEX
    Explanations

    entity actions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Об
    0.74
    Equals
    0.72
    လည်း
    0.71
     Несмотря
    0.69
    От
    0.68
    Под
    0.68
     й
    0.68
    Tambah
    0.68
    Retour
    0.67
    Ook
    0.67
    POSITIVE LOGITS
    ®
    1.35
    ™
    1.26
     ஆகியவை
    1.25
     ஆகியோர்
    1.17
     etc
    1.07
    ®,
    1.07
    <sup>
    1.04
    ™,
    1.04
    之类的
    1.02
     ஆகிய
    1.01
    Act Density 0.144%

    No Known Activations