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

    Neuronpedia

    INDEX
    Explanations

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aecat
    0.43
     času
    0.42
    atasaray
    0.39
    ствовали
    0.38
    ampunk
    0.38
     polymerized
    0.38
    psons
    0.37
    heba
    0.37
     líquido
    0.36
    νης
    0.36
    POSITIVE LOGITS
    ↵
    0.55
    0.41
    介绍
    0.38
    ↵↵
    0.37
    </h2>
    0.36
    Note
    0.35
     Footer
    0.35
    ो
    0.35
     Thought
    0.35
     CORE
    0.35
    Act Density 0.002%

    No Known Activations