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

    Neuronpedia

    INDEX
    Explanations

    code integer representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    names
    0.88
     Names
    0.79
    壮
    0.78
     lname
    0.75
    toISOString
    0.74
     نام
    0.72
    werp
    0.71
     नाम
    0.70
    rownames
    0.70
     itemName
    0.69
    POSITIVE LOGITS
     codes
    1.50
     code
    1.41
     códigos
    1.40
     Codes
    1.37
    码
    1.30
    Code
    1.29
     Code
    1.29
     код
    1.26
    codes
    1.21
    Codes
    1.21
    Act Density 0.317%

    No Known Activations