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

    Neuronpedia

    INDEX
    Explanations

    hierarchical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sns
    -0.07
     snippet
    -0.06
     planting
    -0.06
     Lantern
    -0.06
    Pad
    -0.06
    +%
    -0.06
     observes
    -0.06
    нд
    -0.06
    anol
    -0.06
     뿐
    -0.06
    POSITIVE LOGITS
     hierarchy
    0.15
     hierarchical
    0.14
    ierarchy
    0.13
     Hier
    0.12
     hier
    0.11
    Hier
    0.10
     priorities
    0.08
    _hierarchy
    0.08
    Hierarchy
    0.08
    onomy
    0.08
    Act Density 0.006%

    No Known Activations