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

    Neuronpedia

    INDEX
    Explanations

    loan terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heritage
    -0.07
    	sprite
    -0.07
    帮忙
    -0.06
     Intr
    -0.06
    羚
    -0.06
    actic
    -0.06
    uncios
    -0.06
    umer
    -0.06
    tagName
    -0.06
     Qué
    -0.06
    POSITIVE LOGITS
    ‼
    0.08
    撤
    0.07
     график
    0.07
     финанс
    0.07
    //------------------------------------------------------------------------------------------------
    0.07
     Ended
    0.07
    守
    0.07
     Conclusion
    0.07
    ✖
    0.06
     Rihanna
    0.06
    Act Density 0.032%

    No Known Activations