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

    Neuronpedia

    INDEX
    Explanations

    onset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rock
    -0.08
    ka
    -0.07
    sob
    -0.07
     suction
    -0.06
     purpose
    -0.06
    (compare
    -0.06
    KA
    -0.06
    (Member
    -0.06
     Rock
    -0.06
    so
    -0.06
    POSITIVE LOGITS
     :-
    0.07
    ()."
    0.07
     berg
    0.06
     rootReducer
    0.06
     bakeka
    0.06
     ihtiy
    0.06
    ал
    0.06
    adoop
    0.06
    >#
    0.06
     Ανα
    0.06
    Act Density 0.008%

    No Known Activations