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

    Neuronpedia

    INDEX
    Explanations

    time series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interventions
    0.51
    सू
    0.50
     به
    0.48
     intervención
    0.47
    mien
    0.47
     չ
    0.46
    évén
    0.46
     eril
    0.46
    充分
    0.45
     سو
    0.45
    POSITIVE LOGITS
    ったら
    0.50
     Grandma
    0.50
     READING
    0.50
     FORE
    0.49
     Amtrak
    0.48
     TAR
    0.48
     Blockchain
    0.46
    当たり
    0.46
     RESEARCH
    0.46
     RETURNS
    0.45
    Act Density 0.001%

    No Known Activations