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

    Neuronpedia

    INDEX
    Explanations

    continuing or adding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schema
    0.38
     Skin
    0.35
     usually
    0.35
     Bonjour
    0.35
     사용하는
    0.34
    边界
    0.34
     American
    0.34
     Bootstrap
    0.34
     Debug
    0.33
     Wizard
    0.33
    POSITIVE LOGITS
     menambahkan
    0.79
     melanjutkan
    0.71
     added
    0.70
    繼續
    0.68
     மேலும்
    0.66
     pokrač
    0.66
     доба
    0.66
     continuare
    0.66
     continued
    0.65
    added
    0.65
    Act Density 0.002%

    No Known Activations