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

    Neuronpedia

    INDEX
    Explanations

    numbered parameters or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invited
    1.45
    invited
    1.43
     quietly
    1.43
     internalized
    1.42
     undersigned
    1.35
     merely
    1.35
     scramble
    1.32
    則是
    1.32
     comorbidities
    1.32
    iron
    1.32
    POSITIVE LOGITS
    𝚝
    1.58
    𝚊
    1.56
     llevando
    1.48
    ل
    1.47
    𝘵
    1.40
    ত্ব
    1.38
    ために
    1.37
    agner
    1.35
    𝘢
    1.34
    ein
    1.33
    Act Density 0.000%

    No Known Activations