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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.08
    𬬻
    -0.08
    .work
    -0.07
    omnia
    -0.07
    不利
    -0.07
    нд
    -0.07
     upstream
    -0.07
    fi
    -0.07
     buddies
    -0.06
    ализ
    -0.06
    POSITIVE LOGITS
    科学家
    0.08
    庠
    0.07
     sequ
    0.07
    心思
    0.07
     Science
    0.07
    _jet
    0.07
     получен
    0.07
     McLaren
    0.07
     strap
    0.07
    ,length
    0.07
    Act Density 0.041%

    No Known Activations