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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     en
    -1.73
     En
    -1.38
    En
    -1.12
    ton
    -0.94
     EN
    -0.94
    day
    -0.90
    DAY
    -0.66
     mis
    -0.61
     én
    -0.60
     in
    -0.57
    POSITIVE LOGITS
     ―――――
    0.95
     Theſe
    0.93
     Houſe
    0.93
    ✨:
    0.90
     doubtnut
    0.89
     photolibrary
    0.88
     itſelf
    0.86
     Jefus
    0.86
    Приятного
    0.85
     leſs
    0.85
    Act Density 0.088%

    No Known Activations