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

    Neuronpedia

    INDEX
    Explanations

    flow direction or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Expand
    0.47
     Steering
    0.44
     Roadmap
    0.43
    luk
    0.43
     expand
    0.42
    Bre
    0.41
    BEN
    0.41
    Expand
    0.41
     Bre
    0.40
     Magn
    0.39
    POSITIVE LOGITS
     উঠলো
    0.50
    ↓
    0.49
     ↑
    0.45
    uparrow
    0.45
     উঠেছিল
    0.45
    ⤴
    0.44
    上がる
    0.44
     ascendent
    0.44
     ↓
    0.43
    죵
    0.42
    Act Density 0.000%

    No Known Activations