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

    Neuronpedia

    INDEX
    Explanations

    how I can help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÕES
    0.96
    പറ
    0.88
     recommending
    0.87
     recommend
    0.85
     honestly
    0.84
    ões
    0.81
    教えて
    0.80
    hesians
    0.79
     yourself
    0.79
     บอก
    0.77
    POSITIVE LOGITS
     Remain
    0.79
     Day
    0.64
     Additional
    0.58
     day
    0.57
    overlapping
    0.57
     남아
    0.56
     remained
    0.56
     differed
    0.54
     המת
    0.54
    ிலும்
    0.53
    Act Density 0.142%

    No Known Activations