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

    Neuronpedia

    INDEX
    Explanations

    ESG rating, patient similarity, fairness, controlling, possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acrob
    0.50
     breasts
    0.49
    Боль
    0.48
     stainless
    0.46
    크
    0.46
     estadística
    0.45
     ursprünglich
    0.45
     pleasantly
    0.45
     extin
    0.45
     extend
    0.44
    POSITIVE LOGITS
     Conditional
    0.51
     Backward
    0.49
     Theology
    0.49
    SpawnEntry
    0.49
     Shadows
    0.49
     Du
    0.48
     Modeling
    0.47
     Components
    0.46
     Comparative
    0.45
    irme
    0.45
    Act Density 0.002%

    No Known Activations