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

    Neuronpedia

    INDEX
    Explanations

    code snippets after common punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    则是
    0.27
     largely
    0.25
     която
    0.24
    )
    0.24
    基本的に
    0.24
     validates
    0.24
     என்பதை
    0.24
    ם
    0.24
    都是
    0.24
    為主
    0.24
    POSITIVE LOGITS
    try
    0.29
    setState
    0.29
    eared
    0.29
    did
    0.29
    vocab
    0.28
    eos
    0.27
    newpage
    0.27
    new
    0.26
    faa
    0.26
     bağ
    0.26
    Act Density 0.042%

    No Known Activations