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

    Neuronpedia

    INDEX
    Explanations

    strategy and winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     application
    0.43
     jh
    0.42
    application
    0.40
     subspecies
    0.39
     ne
    0.39
     लेख
    0.39
     subdomain
    0.39
     ning
    0.38
     वैसा
    0.38
     inferiority
    0.38
    POSITIVE LOGITS
    Routine
    0.48
    Bets
    0.48
    Pizza
    0.46
    Choose
    0.46
    ബു
    0.45
     ബു
    0.45
     Bethel
    0.45
    Galaxy
    0.45
    玦
    0.45
     Routine
    0.44
    Act Density 0.016%

    No Known Activations