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

    Neuronpedia

    INDEX
    Explanations

    guide preparation and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bbR
    0.41
     intramuscular
    0.40
     mêmes
    0.40
     даже
    0.39
     السعودي
    0.39
     estimation
    0.39
    même
    0.39
    だけでなく
    0.39
     สัก
    0.39
     самой
    0.38
    POSITIVE LOGITS
     Wallace
    0.42
    ቛ
    0.41
     புற
    0.41
    yre
    0.40
    Britain
    0.39
    ąda
    0.39
    wyd
    0.38
     बता
    0.38
    ophenone
    0.38
    Eth
    0.38
    Act Density 0.001%

    No Known Activations