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

    Neuronpedia

    INDEX
    Explanations

    rich description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒔
    1.30
     achieving
    1.19
    𝒏
    1.13
    știg
    1.07
    equations
    1.05
    回事
    1.05
    ગ્ર
    1.04
    высо
    1.04
     HIGH
    1.04
     उच्च
    1.03
    POSITIVE LOGITS
    多彩
    1.65
    शाली
    1.52
     trove
    1.38
    MOND
    1.37
    rich
    1.29
    ochet
    1.25
     detalhes
    1.25
     vein
    1.24
    yl
    1.21
    iseite
    1.18
    Act Density 0.059%

    No Known Activations