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

    Neuronpedia

    INDEX
    Explanations

    contextual understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     br
    1.48
    br
    1.48
    BR
    1.41
    Br
    1.24
    bru
    1.20
    break
    1.12
    Ocean
    1.08
     Br
    1.06
     BR
    1.05
    bris
    1.05
    POSITIVE LOGITS
    ual
    1.98
    ually
    1.70
     createContext
    1.39
    ualmente
    1.30
     context
    1.24
     clues
    1.24
    ualan
    1.21
    uele
    1.17
     contexts
    1.16
    codingPath
    1.14
    Act Density 0.062%

    No Known Activations