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

    Neuronpedia

    INDEX
    Explanations

    questions and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    乾隆
    0.38
     प्रवाह
    0.38
     `%
    0.36
     प्रत्येक
    0.35
    yani
    0.35
    प्ली
    0.34
     Alabama
    0.34
     технику
    0.33
     \%
    0.33
    ᵕ
    0.33
    POSITIVE LOGITS
     gxf
    0.40
    RW
    0.39
    Painter
    0.38
    ᚐ
    0.38
    懋
    0.38
    ុស
    0.37
     cercanos
    0.37
     háb
    0.37
     moneys
    0.37
     puesta
    0.36
    Act Density 0.000%

    No Known Activations