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

    Neuronpedia

    INDEX
    Explanations

    pondering questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponibilidade
    0.41
    OrCreate
    0.40
     твор
    0.39
     annuity
    0.39
    لیک
    0.38
     δρα
    0.38
    變得
    0.38
     awareness
    0.38
     mudança
    0.38
     consapevole
    0.37
    POSITIVE LOGITS
     Poh
    0.50
     poh
    0.49
    pok
    0.47
     PO
    0.46
     pondering
    0.45
    Pok
    0.45
     Poincaré
    0.44
     questioning
    0.44
     defi
    0.44
     Poch
    0.43
    Act Density 0.000%

    No Known Activations