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

    Neuronpedia

    INDEX
    Explanations

    configuration setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aton
    0.39
     эмоциона
    0.39
     espont
    0.38
     rhinoceros
    0.38
     amyl
    0.37
    情緒
    0.37
     sangue
    0.36
     مرض
    0.36
     fenómenos
    0.36
     turbidity
    0.36
    POSITIVE LOGITS
     configured
    0.71
     configuring
    0.69
     configure
    0.69
     configuration
    0.65
    配置
    0.64
    定义
    0.64
     Configure
    0.64
     Configuration
    0.62
     konfigur
    0.59
     Configuring
    0.59
    Act Density 0.691%

    No Known Activations