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

    Neuronpedia

    INDEX
    Explanations

    harmful chemicals in cigarettes/vapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anyahu
    0.42
     FON
    0.40
     CA
    0.38
     aldrig
    0.38
     ஓ
    0.37
    ปฏิบัติ
    0.37
     खे
    0.36
     Progressives
    0.36
     CRUZ
    0.35
    UN
    0.35
    POSITIVE LOGITS
     Sargent
    0.39
    mują
    0.39
     straightened
    0.39
    깥
    0.39
    ză
    0.39
    ⇰
    0.38
     frown
    0.37
     climat
    0.37
    део
    0.37
    acă
    0.37
    Act Density 0.000%

    No Known Activations