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

    Neuronpedia

    INDEX
    Explanations

    names, places, and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.77
    ة
    0.74
    ed
    0.72
    0
    0.68
    0.64
      
    0.62
     &
    0.62
     (
    0.61
    a
    0.59
    is
    0.58
    POSITIVE LOGITS
     pissed
    0.96
     disagreeable
    0.83
    ulé
    0.80
    光滑
    0.79
     alarmed
    0.79
     Букмекерлар
    0.79
     españa
    0.79
    扑
    0.79
    ಲ್
    0.78
    铑
    0.78
    Act Density 0.000%

    No Known Activations