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

    Neuronpedia

    INDEX
    Explanations

    consulting, retail, adoption, services, bulbs, block path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recirculation
    0.48
     eigenvalue
    0.47
     lecithin
    0.46
     resonators
    0.46
     clarifying
    0.46
     investigation
    0.46
     tenant
    0.46
     nuances
    0.45
     linearity
    0.45
     linen
    0.45
    POSITIVE LOGITS
    愪
    0.56
    Như
    0.55
    IActions
    0.53
    ﺎ
    0.53
    Ui
    0.52
    Maggie
    0.50
    followfollow
    0.50
    Indians
    0.50
    Am
    0.50
    Morgan
    0.49
    Act Density 0.001%

    No Known Activations