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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kali
    -0.07
    reff
    -0.07
     petroleum
    -0.07
    ellij
    -0.07
    dělen
    -0.07
     교
    -0.06
     ridic
    -0.06
     Heavy
    -0.06
     Giáo
    -0.06
    ्ययन
    -0.06
    POSITIVE LOGITS
    ınma
    0.07
    иболее
    0.07
     situaci
    0.07
     Stamford
    0.06
    langle
    0.06
     ''
↵
    0.06
    LookAndFeel
    0.06
    225
    0.06
    (mm
    0.06
     Texans
    0.06
    Act Density 0.004%

    No Known Activations