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

    Neuronpedia

    INDEX
    Explanations

    interesting followed by a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    0.88
    ımız
    0.85
    ли
    0.84
    ،
    0.83
     of
    0.82
    ش
    0.82
    </h2>
    0.80
    ↵
    0.80
    ımızın
    0.80
     ਇੱਕ
    0.80
    POSITIVE LOGITS
    in
    1.09
    a
    0.98
    id
    0.93
    interesting
    0.86
     interesting
    0.85
    ור
    0.85
     interessante
    0.85
    ul
    0.83
    ма
    0.83
    .
    0.81
    Act Density 0.013%

    No Known Activations