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

    Neuronpedia

    INDEX
    Explanations

    order/position

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.79
    ArrowToggle
    -0.75
     DEVELOPMENT
    -0.75
    enumi
    -0.74
    Development
    -0.72
     estekak
    -0.71
     &___
    -0.69
     transfieras
    -0.69
    PreferredItem
    -0.69
    RegistryLite
    -0.69
    POSITIVE LOGITS
     L
    0.55
     first
    0.47
     BR
    0.46
     less
    0.46
     emerging
    0.46
     under
    0.45
     upper
    0.45
     fast
    0.43
     rapidly
    0.43
     middle
    0.42
    Act Density 0.000%

    No Known Activations