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

    Neuronpedia

    INDEX
    Explanations

    words in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.47
    Насе
    0.46
    Спа
    0.44
    Galaxy
    0.43
    ר
    0.43
    GetAll
    0.42
    ז
    0.42
    קי
    0.42
    З
    0.42
    Get
    0.42
    POSITIVE LOGITS
     moest
    0.53
     käs
    0.51
     मीनिंग
    0.49
    讐
    0.47
     laranja
    0.46
    膾
    0.46
     mõ
    0.46
     ਸੀ
    0.45
     änd
    0.45
     ܘ
    0.45
    Act Density 0.001%

    No Known Activations