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

    Neuronpedia

    INDEX
    Explanations

    open source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ラ
    0.52
    ച്ച്
    0.48
     DOI
    0.48
    IN
    0.47
    AN
    0.46
     celebra
    0.46
    га
    0.45
     mediante
    0.45
    ]}"
    0.45
     tarefa
    0.44
    POSITIVE LOGITS
     אבל
    0.48
    texte
    0.48
    ası
    0.46
     חלק
    0.46
    }}(\
    0.46
     świata
    0.45
     或者
    0.45
    leri
    0.44
    inks
    0.44
     επισ
    0.43
    Act Density 0.001%

    No Known Activations