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

    Neuronpedia

    INDEX
    Explanations

    exclamations followed by jokes or lighthearted phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fata
    0.68
     bilateral
    0.68
     overview
    0.66
     mengatur
    0.64
     infra
    0.62
     determine
    0.62
     diagram
    0.61
     sections
    0.61
     rectification
    0.59
     purview
    0.57
    POSITIVE LOGITS
    Honestly
    0.90
    Haha
    0.89
     Seriously
    0.88
     Honestly
    0.88
    haha
    0.86
     😉
    0.86
    But
    0.83
    Seriously
    0.83
    哈哈哈
    0.82
     Haha
    0.81
    Act Density 0.086%

    No Known Activations