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

    Neuronpedia

    INDEX
    Explanations

    LLM, systems, technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    циями
    0.50
    ക്ടര്‍
    0.45
    ska
    0.44
    ম্বা
    0.43
     ανέ
    0.42
    ڈا
    0.42
    season
    0.42
     marzo
    0.42
    spice
    0.42
    rington
    0.41
    POSITIVE LOGITS
     база
    0.55
     한국
    0.52
     библиотека
    0.50
    ጅም
    0.47
    Sil
    0.46
    Universidad
    0.46
    起動
    0.46
     expedi
    0.46
    ба
    0.45
    ဆက်
    0.45
    Act Density 0.000%

    No Known Activations