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

    Neuronpedia

    INDEX
    Explanations

    climate change, fiscal policy, world war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     són
    0.47
     Flü
    0.43
     neces
    0.43
     labai
    0.42
    לו
    0.42
     mutta
    0.41
     nera
    0.41
     levar
    0.41
     só
    0.39
     Moreira
    0.39
    POSITIVE LOGITS
     ampere
    1.36
     adenine
    1.32
     einigen
    1.02
     furthermore
    1.02
     unmittel
    1.02
     gesamte
    1.00
     hintergrund
    1.00
    Dieser
    0.98
     wichtig
    0.98
     haupt
    0.97
    Act Density 0.005%

    No Known Activations