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

    Neuronpedia

    INDEX
    Explanations

    Motrin Rin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayvachi
    0.44
    ᚋ
    0.42
    httparty
    0.40
    퐶
    0.40
    Ë
    0.39
     rufo
    0.39
     Sandy
    0.39
    gast
    0.39
    䒴
    0.38
    ტის
    0.38
    POSITIVE LOGITS
     trình
    1.79
    程
    1.07
     rin
    1.04
    rin
    0.99
     Rin
    0.98
     RIN
    0.96
    RIN
    0.92
    rine
    0.91
     rinse
    0.90
    рин
    0.88
    Act Density 0.005%

    No Known Activations