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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणखी
    0.91
    另一种
    0.85
    还有一个
    0.85
     други
    0.80
     또
    0.75
     swap
    0.75
    வில்லை
    0.74
     fracking
    0.73
    "/><
    0.73
     hinzufügen
    0.72
    POSITIVE LOGITS
     II
    1.16
     Section
    1.15
    section
    1.10
     section
    1.07
    II
    1.07
     III
    1.07
     Sections
    1.05
    Section
    1.03
    一
    1.02
     SECTION
    1.02
    Act Density 0.589%

    No Known Activations