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

    Neuronpedia

    INDEX
    Explanations

    explaining something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pharmacy
    0.45
    กิน
    0.44
    有用
    0.44
    クリル
    0.44
    ッセージ
    0.43
    食べる
    0.42
     highland
    0.42
    クロマト
    0.42
     жидкости
    0.42
     liquef
    0.42
    POSITIVE LOGITS
     Cumbria
    0.51
     Cllr
    0.47
     Cheltenham
    0.47
    Cllr
    0.46
     doesn
    0.46
     creates
    0.46
     Swindon
    0.45
     Brighton
    0.45
     ensures
    0.45
     Slade
    0.45
    Act Density 0.006%

    No Known Activations