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

    Neuronpedia

    INDEX
    Explanations

    construction projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Аль
    -0.79
     öffnet
    -0.78
    ម
    -0.78
    ématiques
    -0.77
    vide
    -0.77
     саду
    -0.76
     melay
    -0.75
    ériques
    -0.75
     malas
    -0.73
     saucepan
    -0.73
    POSITIVE LOGITS
     projects
    1.41
     project
    1.34
     rehabilit
    1.09
     contractor
    1.09
     rehabilitation
    1.02
     equipping
    0.97
     contractors
    0.96
     rehabilitate
    0.95
    projects
    0.95
     completed
    0.94
    Act Density 0.006%

    No Known Activations