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

    Neuronpedia

    INDEX
    Explanations

    ultimate question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stabil
    0.38
    Stabil
    0.36
    塚
    0.36
    COMMENT
    0.35
    oxid
    0.34
     cushioning
    0.34
    margin
    0.34
     रखें
    0.34
    emp
    0.34
    绣
    0.33
    POSITIVE LOGITS
     willfully
    0.39
     Consultancy
    0.39
    蒇
    0.38
    哄
    0.38
     Gb
    0.38
     consultancy
    0.37
     আহ
    0.37
    ullie
    0.37
     declaratory
    0.37
     Bungal
    0.37
    Act Density 0.003%

    No Known Activations