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

    Neuronpedia

    INDEX
    Explanations

    generate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ViewController
    1.00
    ┉
    1.00
     \%\
    0.99
    ResumeLayout
    0.99
    镜
    0.96
     %@",
    0.96
     disguise
    0.94
    𝗹
    0.94
     மேற்க
    0.94
     Taxonomic
    0.93
    POSITIVE LOGITS
    m
    1.05
     esse
    1.03
     consenso
    1.02
    ve
    0.98
    ق
    0.96
     впечатление
    0.95
    ड
    0.94
    𝐝
    0.94
    rafts
    0.92
    d
    0.92
    Act Density 0.246%

    No Known Activations