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

    Neuronpedia

    INDEX
    Explanations

    do you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まさ
    0.78
    There
    0.76
    Usage
    0.76
    there
    0.76
     опыт
    0.76
    thane
    0.75
     Usage
    0.74
    вості
    0.70
     itibaren
    0.70
    doubt
    0.70
    POSITIVE LOGITS
    omsday
    1.20
     justice
    1.18
    zens
    1.16
    ppel
    1.07
     wonders
    1.07
     things
    1.05
     laundry
    1.03
     unto
    1.02
     something
    0.99
     away
    0.96
    Act Density 0.191%

    No Known Activations