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

    Neuronpedia

    INDEX
    Explanations

    experimentation and innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stately
    0.41
     denars
    0.37
    authenticated
    0.36
    rać
    0.36
     bağlan
    0.36
     specifies
    0.35
    現實
    0.35
     serviceable
    0.35
     વ્યવ
    0.35
    镑
    0.34
    POSITIVE LOGITS
     experimentation
    1.83
     experimenting
    1.75
     speriment
    1.52
     экспери
    1.50
     Experiment
    1.48
    创新
    1.47
     innovate
    1.47
     experiment
    1.46
    Experiment
    1.46
     innovation
    1.45
    Act Density 0.024%

    No Known Activations