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

    Neuronpedia

    INDEX
    Explanations

    Important considerations and tips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marissa
    0.61
     zmdi
    0.60
     Susanne
    0.60
     Millennium
    0.59
    品质
    0.59
     Bur
    0.59
    Blitz
    0.59
     BUR
    0.59
    ̃
    0.59
     Benny
    0.58
    POSITIVE LOGITS
    ара
    0.64
     autora
    0.62
    ods
    0.61
    rafl
    0.60
     காற்ற
    0.59
    getAs
    0.59
    release
    0.57
     알아
    0.57
    retryWrites
    0.57
     Author
    0.57
    Act Density 0.132%

    No Known Activations