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

    Neuronpedia

    INDEX
    Explanations

    qualitative descriptions of states or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Everyone
    0.43
    我们
    0.41
    everyone
    0.41
    át
    0.40
     我们
    0.39
    Deleting
    0.39
    HERE
    0.39
     burada
    0.39
    Fant
    0.38
    电路
    0.38
    POSITIVE LOGITS
     consultation
    0.43
    ochromatic
    0.43
     cricket
    0.41
     appreciation
    0.39
     consistency
    0.39
     Ayurvedic
    0.39
     dioxane
    0.38
     learnings
    0.38
     histori
    0.37
     mutations
    0.37
    Act Density 0.007%

    No Known Activations