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

    Neuronpedia

    INDEX
    Explanations

    inflation rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Against
    0.38
    しまった
    0.37
    MaxIntensity
    0.37
     сопер
    0.36
     семь
    0.36
    cca
    0.35
    윕
    0.35
    amina
    0.35
    相当于
    0.34
    しますが
    0.34
    POSITIVE LOGITS
     Variante
    0.43
     Bildung
    0.42
     generated
    0.42
     generation
    0.41
     generación
    0.41
     seen
    0.40
     Erfahrung
    0.40
     dilihat
    0.40
     bartender
    0.40
     Educação
    0.39
    Act Density 0.000%

    No Known Activations