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

    Neuronpedia

    INDEX
    Explanations

    specific aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unmist
    0.83
    entrée
    0.81
    тит
    0.71
     Key
    0.70
    key
    0.69
     spiega
    0.69
     ключе
    0.68
    剜
    0.68
     clé
    0.68
     Explained
    0.68
    POSITIVE LOGITS
     aspect
    2.53
     aspects
    2.44
     Aspect
    2.43
    Aspect
    2.33
     Aspects
    2.25
    aspect
    2.21
     aspectos
    2.10
     ASPECT
    2.07
     ASPECTS
    2.07
     aspek
    2.03
    Act Density 0.085%

    No Known Activations