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

    Neuronpedia

    INDEX
    Explanations

    abstract, abstract interpretation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Joss
    0.39
     unidos
    0.37
     gente
    0.37
    aters
    0.36
    oglobin
    0.35
    ameni
    0.35
     ***!
    0.35
     chor
    0.34
    लाइ
    0.34
    міністра
    0.34
    POSITIVE LOGITS
     abstract
    1.23
     Abstract
    1.21
    abstract
    1.10
    Abstract
    1.09
    抽象
    1.02
     abstracto
    0.98
     абстра
    0.96
     ABSTRACT
    0.96
     abstracts
    0.95
     abstrak
    0.91
    Act Density 0.002%

    No Known Activations