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

    Neuronpedia

    INDEX
    Explanations

    introduces lists or facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚈
    0.47
     LTD
    0.44
    love
    0.42
     setInterval
    0.42
    ğinde
    0.42
     SIAM
    0.42
    видно
    0.41
    🔼
    0.41
    🈺
    0.41
     entitle
    0.40
    POSITIVE LOGITS
     chercheurs
    0.49
     périph
    0.47
    ヂストン
    0.47
     molécules
    0.46
     ajout
    0.45
    доо
    0.45
    ك
    0.45
     veux
    0.45
    自
    0.44
    資源
    0.44
    Act Density 0.002%

    No Known Activations