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

    Neuronpedia

    INDEX
    Explanations

    endless opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ियल
    0.57
     Customer
    0.51
     Bad
    0.50
     old
    0.49
     SONS
    0.49
     Birth
    0.49
     Experts
    0.48
     Ear
    0.48
     Shares
    0.48
     Guilford
    0.48
    POSITIVE LOGITS
    ᅬ
    0.44
    мпа
    0.42
    ᒋ
    0.39
     ster
    0.39
     ጉዳ
    0.38
    اين
    0.38
    쾨
    0.38
    pherd
    0.38
    Stephanie
    0.38
    ydro
    0.37
    Act Density 0.002%

    No Known Activations