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

    Neuronpedia

    INDEX
    Explanations

    finalizing arrangements and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xhr
    1.09
     EditText
    1.09
     varchar
    1.09
    Појединачна
    1.08
     officers
    1.06
     inFile
    1.06
    いますが
    1.06
     extremal
    1.04
     Bxd
    1.03
     eigenvalue
    1.03
    POSITIVE LOGITS
    bruk
    1.32
    ات
    1.24
    ের
    1.22
    atta
    1.22
    륨
    1.17
    ஸ்ட
    1.16
    এর
    1.14
    лен
    1.14
    1.14
    lane
    1.13
    Act Density 0.001%

    No Known Activations