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

    Neuronpedia

    INDEX
    Explanations

    starts with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     важней
    0.74
     एक्सपेरिमेंट
    0.73
     viktigt
    0.69
     tärke
    0.69
     imprescindible
    0.68
     penting
    0.66
     ważne
    0.66
    experiment
    0.65
     জরুরি
    0.65
    ামী
    0.65
    POSITIVE LOGITS
     optics
    0.88
     purview
    0.83
     oversight
    0.81
     factual
    0.79
     timelines
    0.77
     anim
    0.76
     derel
    0.75
     latitude
    0.75
     deliverables
    0.74
     semblance
    0.72
    Act Density 0.040%

    No Known Activations