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

    Neuronpedia

    INDEX
    Explanations

    creation of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.08
    ле
    0.99
    服务
    0.98
    ,
    0.96
    、
    0.93
    ü
    0.90
    د
    0.87
    J
    0.82
    。「
    0.79
    It
    0.78
    POSITIVE LOGITS
     creation
    1.13
     in
    1.05
     Creation
    0.99
    creation
    0.98
    nya
    0.81
    macro
    0.80
    Creation
    0.79
    evolution
    0.76
    ride
    0.75
    ’.
    0.75
    Act Density 0.017%

    No Known Activations