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

    Neuronpedia

    INDEX
    Explanations

    importing libraries or modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '[
    0.73
     mycorrh
    0.70
     [.
    0.64
     영
    0.63
     Pluto
    0.62
     "[
    0.62
     Nirvana
    0.62
     bravo
    0.62
     nexus
    0.62
     subcut
    0.61
    POSITIVE LOGITS
     import
    0.79
    库
    0.57
    模块
    0.54
     用于
    0.54
    import
    0.53
     imported
    0.51
     importar
    0.50
    包
    0.49
     থেকেও
    0.48
     library
    0.48
    Act Density 0.184%

    No Known Activations