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

    Neuronpedia

    INDEX
    Explanations

    using techniques and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    件事情
    0.42
    事情
    0.42
    тері
    0.40
     मायने
    0.40
    requirement
    0.38
    的事情
    0.38
    ovaní
    0.38
    ാര്യ
    0.37
     kurie
    0.37
    étape
    0.37
    POSITIVE LOGITS
     techniques
    0.90
     tools
    0.82
     tactics
    0.79
     técnicas
    0.77
     resources
    0.73
     herramientas
    0.71
     sparingly
    0.70
     methods
    0.70
     métodos
    0.66
     방법을
    0.66
    Act Density 0.113%

    No Known Activations