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

    Neuronpedia

    INDEX
    Explanations

    specific concepts or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сам
    0.40
    this
    0.39
     нашего
    0.39
     our
    0.38
     overcomes
    0.37
    oliath
    0.36
     আমাদের
    0.36
    ология
    0.35
    사와
    0.35
    ilion
    0.34
    POSITIVE LOGITS
     Alguns
    0.54
     Certaines
    0.51
     bazı
    0.51
     Certains
    0.50
     Algunas
    0.47
     niektórych
    0.46
     Beberapa
    0.46
     frases
    0.46
     አንዳንድ
    0.45
     antaranya
    0.45
    Act Density 0.009%

    No Known Activations