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

    Neuronpedia

    INDEX
    Explanations

    foreign words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ात
    2.01
    اً
    1.83
    сть
    1.76
    ু
    1.73
    ኑ
    1.66
    ార్క్
    1.65
    থেষ্ট
    1.63
    ید
    1.62
    )})$
    1.62
    ଦ
    1.57
    POSITIVE LOGITS
    tok
    1.95
    総合
    1.91
     residue
    1.85
    ल
    1.83
    nb
    1.82
     것
    1.76
     embracing
    1.76
    1.76
     खासा
    1.75
    Regards
    1.73
    Act Density 0.000%

    No Known Activations