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

    Neuronpedia

    INDEX
    Explanations

    performance relative to size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Differences
    0.38
     momentary
    0.37
     دائ
    0.35
    rospection
    0.34
     대신
    0.34
    যত
    0.34
     endTime
    0.34
    纖
    0.34
     เพราะ
    0.33
     prevents
    0.33
    POSITIVE LOGITS
     relative
    0.60
     despite
    0.57
    relative
    0.55
    despite
    0.54
     consistently
    0.54
    RELATIVE
    0.53
     rival
    0.52
     cementing
    0.51
     Despite
    0.50
     relativo
    0.50
    Act Density 0.012%

    No Known Activations