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

    Neuronpedia

    INDEX
    Explanations

    The Trevor National Lucy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cry
    0.37
     Cri
    0.37
     CRY
    0.36
    FormProvider
    0.36
     кри
    0.36
     cox
    0.35
    靠
    0.35
     लग
    0.34
     cry
    0.34
     cri
    0.34
    POSITIVE LOGITS
     THER
    0.42
    Neuro
    0.41
    Lucy
    0.41
    Ther
    0.40
     lu
    0.40
     Lucifer
    0.39
     Tugas
    0.39
    ifères
    0.38
    THER
    0.38
     Neuro
    0.38
    Act Density 0.014%

    No Known Activations