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

    Neuronpedia

    INDEX
    Explanations

    philosophical to shame and movies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    docs
    0.49
    processes
    0.47
    *
    0.47
    cannot
    0.46
     hear
    0.45
     fruta
    0.45
    process
    0.44
    cargo
    0.44
    _
    0.43
     আহম্মদ
    0.43
    POSITIVE LOGITS
     탄
    0.49
    識
    0.45
     диамет
    0.44
     క్యా
    0.43
     tenement
    0.43
    zący
    0.43
     ಔ
    0.42
    捞
    0.42
     우
    0.42
     maximising
    0.42
    Act Density 0.003%

    No Known Activations