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

    Neuronpedia

    INDEX
    Explanations

    origin or significant event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outras
    0.42
     Suitable
    0.38
     Aspects
    0.38
     aspects
    0.37
    đa
    0.37
     Thereafter
    0.37
    ۔۔۔۔
    0.37
     کرے
    0.37
     інших
    0.37
     both
    0.36
    POSITIVE LOGITS
     aftermath
    0.68
     recently
    0.65
     infamous
    0.61
     finale
    0.54
     announcement
    0.54
     notorious
    0.54
    recently
    0.53
     fallout
    0.52
     annual
    0.52
     recientemente
    0.52
    Act Density 0.054%

    No Known Activations