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

    Neuronpedia

    INDEX
    Explanations

    abstract interfaces and base classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jTextField
    0.74
     intron
    0.73
     nouvelle
    0.72
     entrar
    0.72
     집중
    0.71
    რის
    0.71
    뚠
    0.71
     nowy
    0.70
     rápida
    0.69
     slander
    0.69
    POSITIVE LOGITS
    abstract
    1.91
    Abstract
    1.81
     abstract
    1.77
     Abstract
    1.73
    Base
    1.68
     Base
    1.65
    抽象
    1.59
     абстра
    1.48
     base
    1.44
    base
    1.43
    Act Density 0.214%

    No Known Activations