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

    Neuronpedia

    INDEX
    Explanations

    Alice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differenti
    2.20
    등
    2.09
    嬠
    2.09
    𝘇
    2.09
    ᆼ
    2.06
    有着
    2.05
    在那里
    2.03
     архіви
    2.02
    นี้
    1.99
    在
    1.99
    POSITIVE LOGITS
    am
    2.89
    or
    2.61
    ர்
    2.59
    ine
    2.52
    ara
    2.48
    he
    2.47
    ad
    2.45
    ia
    2.45
    er
    2.38
    al
    2.30
    Act Density 0.114%

    No Known Activations