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

    Neuronpedia

    INDEX
    Explanations

    nomenclature and naming conventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indefinite
    0.42
     impressed
    0.42
     antecedent
    0.39
     enthusiastic
    0.39
     distinctions
    0.39
    hydraulic
    0.38
     primarySwatch
    0.38
     entered
    0.38
     Hydraulic
    0.38
    entet
    0.37
    POSITIVE LOGITS
    mspace
    0.42
     nomencl
    0.42
    ્ટ
    0.38
     Nomenclature
    0.37
    论文
    0.36
    磨
    0.36
    TIP
    0.35
    命名
    0.35
    名单
    0.35
    Tab
    0.35
    Act Density 0.000%

    No Known Activations