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

    Neuronpedia

    INDEX
    Explanations

    Hyun Bin, Manco Capac, Stephen Fry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    1.38
     enforcing
    1.27
    :
    1.20
    v
    1.14
    েল
    1.13
     enforceable
    1.11
    end
    1.10
    iz
    1.10
    i
    1.10
    f
    1.10
    POSITIVE LOGITS
    ع
    1.92
     communément
    1.75
    ς
    1.66
     thoracique
    1.63
    𝐨
    1.61
     možnosti
    1.60
     voisines
    1.59
     syphilis
    1.58
     tortue
    1.55
     moguć
    1.55
    Act Density 0.002%

    No Known Activations