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

    Neuronpedia

    INDEX
    Explanations

    also también także

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basics
    0.56
     generics
    0.55
     glucose
    0.52
     algorithms
    0.51
     regimens
    0.50
     gens
    0.50
     upfront
    0.50
     systems
    0.49
     организма
    0.49
     bespoke
    0.49
    POSITIVE LOGITS
     также
    0.74
    also
    0.65
    Также
    0.65
     tambien
    0.64
     también
    0.62
     też
    0.60
     Cũng
    0.60
    또한
    0.59
     asimismo
    0.59
    Also
    0.58
    Act Density 0.003%

    No Known Activations