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

    Neuronpedia

    INDEX
    Explanations

    finance, institutions, and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     связь
    0.53
     connexion
    0.49
     связи
    0.43
     forbindelse
    0.42
     connection
    0.41
     Verbindung
    0.41
     collegamento
    0.39
     same
    0.38
    нта
    0.38
     anecdote
    0.38
    POSITIVE LOGITS
    gkin
    0.44
    DL
    0.38
     REP
    0.37
    🌖
    0.37
    UCI
    0.37
    erase
    0.37
     architecture
    0.35
    architecture
    0.35
     மனை
    0.35
     ডিস
    0.35
    Act Density 0.001%

    No Known Activations