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

    Neuronpedia

    INDEX
    Explanations

    Forth stack operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retomar
    0.34
     这是
    0.33
     বিধান
    0.32
    навли
    0.32
    Ukraine
    0.32
    包裹
    0.32
     beliebt
    0.31
    াহিয়া
    0.31
     প্রস্তুত
    0.31
    creens
    0.31
    POSITIVE LOGITS
    肺
    0.36
    免疫
    0.34
     glomerul
    0.33
     chronic
    0.32
     malignancies
    0.32
    0
    0.31
     entropy
    0.31
    лез
    0.31
     bladder
    0.31
     cystic
    0.31
    Act Density 0.001%

    No Known Activations