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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    peso
    0.40
    正则
    0.39
    CTime
    0.39
    ..<
    0.38
     مستوى
    0.38
     requester
    0.38
     資
    0.37
    属性
    0.37
    checks
    0.37
    muje
    0.37
    POSITIVE LOGITS
     Transactions
    0.41
     Printed
    0.40
     Impact
    0.38
     Artificial
    0.38
     Witness
    0.37
     Serving
    0.37
     Angular
    0.37
    ABOR
    0.37
     Biblical
    0.36
     Anticip
    0.36
    Act Density 0.000%

    No Known Activations