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

    Neuronpedia

    INDEX
    Explanations

    context tree or context window

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wi
    0.39
     Compact
    0.38
    aff
    0.37
     BufferedImage
    0.37
     mas
    0.37
     larvae
    0.36
    ingen
    0.36
     interim
    0.36
    eno
    0.36
     da
    0.36
    POSITIVE LOGITS
    ual
    0.98
    ually
    0.91
     kontek
    0.79
     контек
    0.78
    UAL
    0.76
    ualmente
    0.74
     contexto
    0.73
     contexte
    0.68
     createContext
    0.66
     contexts
    0.66
    Act Density 0.023%

    No Known Activations