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

    Neuronpedia

    INDEX
    Explanations

    fluctuations and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     droplets
    0.51
     kala
    0.46
     snippet
    0.44
     spasm
    0.44
     parish
    0.43
     fibroblasts
    0.43
     rope
    0.43
     minerales
    0.43
     metabolic
    0.42
     bergerak
    0.42
    POSITIVE LOGITS
    tc
    0.52
    ttt
    0.51
    টায়
    0.48
     Re
    0.47
    㤈
    0.47
     Guess
    0.46
    tt
    0.46
    tti
    0.46
    nThe
    0.45
    Survivor
    0.45
    Act Density 0.002%

    No Known Activations