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

    Neuronpedia

    INDEX
    Explanations

    accept terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rad
    0.42
    polished
    0.42
    INSTALL
    0.40
     instalación
    0.39
    呱
    0.39
    希
    0.38
    放心
    0.37
    皈
    0.36
     Radha
    0.36
     install
    0.36
    POSITIVE LOGITS
     overcrowding
    0.42
     obstacles
    0.40
    瓏
    0.40
     기준
    0.39
     ανε
    0.39
    orys
    0.39
    三个
    0.38
     Needs
    0.38
     তিনটি
    0.38
     crooked
    0.37
    Act Density 0.000%

    No Known Activations