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

    Neuronpedia

    INDEX
    Explanations

    instructions or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    capital
    0.44
    Capital
    0.42
    городе
    0.41
    Church
    0.39
    πτυ
    0.38
    qualification
    0.38
     punishment
    0.38
    significant
    0.38
    გუფი
    0.38
     circulated
    0.37
    POSITIVE LOGITS
     Env
    0.45
     budgets
    0.44
    啶
    0.43
    estries
    0.40
     env
    0.39
     Bud
    0.39
     
    0.38
     contexts
    0.38
     ආ
    0.38
     Buds
    0.38
    Act Density 0.025%

    No Known Activations