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

    Neuronpedia

    INDEX
    Explanations

    st, tr, ch, th, br prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.40
    ний
    0.40
    ↵
    0.39
    ährt
    0.37
    ➰
    0.36
    वैसे
    0.36
    गतान
    0.36
     πολύ
    0.35
     není
    0.35
     dikenal
    0.34
    POSITIVE LOGITS
    c
    0.54
    د
    0.54
     it
    0.51
    ال
    0.42
     embeddings
    0.42
     confir
    0.41
    ból
    0.41
    ก
    0.41
    ام
    0.40
    ت
    0.40
    Act Density 0.059%

    No Known Activations