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

    Neuronpedia

    INDEX
    Explanations

    super and hyper prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tailwind
    0.74
     cuff
    0.73
     pointing
    0.72
     abort
    0.71
     webhook
    0.71
     reshape
    0.70
     glimpse
    0.70
     notably
    0.69
     entree
    0.68
     cornerstone
    0.68
    POSITIVE LOGITS
    active
    1.22
    structure
    1.20
    kinetic
    1.20
    structural
    1.20
    structures
    1.19
    -/
    1.15
    -)
    1.13
    thermal
    1.13
    pro
    1.12
    aliment
    1.11
    Act Density 0.191%

    No Known Activations