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

    Neuronpedia

    INDEX
    Explanations

    dependency or dependence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ז
    0.42
    槓
    0.42
    锹
    0.38
    యర్
    0.38
    प्लाई
    0.38
    ariu
    0.38
    瀵
    0.38
    ز
    0.37
    裵
    0.36
    ماء
    0.36
    POSITIVE LOGITS
    dependency
    0.47
    Dependency
    0.46
    dependence
    0.46
    depend
    0.45
     dependency
    0.44
     Dependency
    0.44
     dependence
    0.43
     dependencies
    0.43
    依赖
    0.42
     Dependence
    0.42
    Act Density 0.002%

    No Known Activations