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

    Neuronpedia

    INDEX
    Explanations

    career paths and advancement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Process
    0.41
    Parameter
    0.38
    eces
    0.37
    Optim
    0.37
    encoding
    0.37
    Vari
    0.36
     budgets
    0.36
    カラ
    0.35
    process
    0.35
    delegate
    0.35
    POSITIVE LOGITS
     path
    0.99
     paths
    0.98
     advancement
    0.96
     progression
    0.93
     Paths
    0.87
     trajectory
    0.86
    path
    0.82
     Advancement
    0.81
     aspirations
    0.80
     trajectories
    0.78
    Act Density 0.008%

    No Known Activations