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

    Neuronpedia

    INDEX
    Explanations

    refusal of harmful requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     harbor
    0.47
     harbors
    0.44
     flavor
    0.44
     flavors
    0.41
     multicolored
    0.40
     Gravel
    0.40
     favorably
    0.39
     Sliver
    0.39
     Harbor
    0.39
    nessy
    0.38
    POSITIVE LOGITS
     nggak
    0.45
     TikTok
    0.45
     चीज़
    0.45
    TikTok
    0.44
     netizens
    0.44
     ख़
    0.43
     एक्सरसा
    0.43
     Pics
    0.43
     personalisation
    0.43
     آ
    0.42
    Act Density 0.009%

    No Known Activations