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

    Neuronpedia

    INDEX
    Explanations

    Diverse excerpts from different sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wyśw
    -0.08
     tipped
    -0.07
    .quiz
    -0.07
    ologne
    -0.07
    קיש
    -0.07
    Dani
    -0.06
     Ibid
    -0.06
     testimonials
    -0.06
     alışver
    -0.06
     tongue
    -0.06
    POSITIVE LOGITS
    alls
    0.08
     communauté
    0.07
    进行
    0.07
    ailability
    0.07
     Rentals
    0.07
    -mar
    0.07
    浦
    0.07
     )↵
    0.07
    مطار
    0.06
     Eine
    0.06
    Act Density 0.003%

    No Known Activations