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

    Neuronpedia

    INDEX
    Explanations

    Quadrupels, [controller] routes, Bank Nifty, I-485

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ा
    0.44
    a
    0.38
     propria
    0.38
    ]-
    0.36
     compliqué
    0.35
     ću
    0.35
    ary
    0.34
     help
    0.33
    ⇓
    0.33
    \|$
    0.33
    POSITIVE LOGITS
    ers
    0.45
    toString
    0.38
    toDouble
    0.37
     Notation
    0.37
    取引
    0.37
    proto
    0.36
    Rồi
    0.36
    ფი
    0.36
    粆
    0.36
    𝘨
    0.36
    Act Density 0.003%

    No Known Activations