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

    Neuronpedia

    INDEX
    Explanations

    matter how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ब्दिक
    0.38
    ئات
    0.37
     वेतन
    0.35
     tanıml
    0.35
     luminos
    0.34
     sylvis
    0.34
    NIOS
    0.34
    㖘
    0.34
     miljø
    0.34
     hyperemia
    0.34
    POSITIVE LOGITS
    Sp
    0.37
    IDA
    0.32
     Cic
    0.32
    Steve
    0.32
    bag
    0.31
     O
    0.30
    CD
    0.29
    MM
    0.29
    토리
    0.29
     B
    0.29
    Act Density 0.000%

    No Known Activations