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

    Neuronpedia

    INDEX
    Explanations

    foundational learning and basics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     advanced
    0.48
     продви
    0.48
     Advanced
    0.45
    先进
    0.42
     avanz
    0.42
    oproject
    0.42
     сложно
    0.41
    ництво
    0.41
     avanzado
    0.41
     avanç
    0.41
    POSITIVE LOGITS
     foundational
    1.12
     basic
    1.05
    basic
    1.02
    基礎
    1.00
    Basic
    0.98
    基础
    0.97
     basics
    0.95
     Grundlagen
    0.94
     fundamental
    0.93
     foundations
    0.93
    Act Density 0.022%

    No Known Activations